MétaCan
Menu
Back to cohort

SAEs Are Good for Steering – If You Select the Right Features

2025· article· W4416036894 on OpenAlexfundno aff
Dana Arad, Aaron Mueller, Yonatan Belinkov

Bibliographic record

Venuenot available
Typearticle
Language
FieldEngineering
TopicVehicle Dynamics and Control Systems
Canadian institutionsnot available
FundersAzrieli FoundationEuropean CommissionOpen Philanthropy Project
KeywordsSet (abstract data type)Feature (linguistics)Matching (statistics)Identification (biology)Key (lock)

Abstract

fetched live from OpenAlex

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space.This enables useful applications such as steeringinfluencing the output of a model towards a desired concept-without requiring labeled data.Current methods identify SAE features to steer by analyzing the input tokens that activate them.However, recent work has highlighted that activations alone do not fully describe the effect of a feature on the model's output.In this work, we draw a distinction between two types of features: input features, which mainly capture patterns in the model's input, and output features, which have a human-understandable effect on the model's output.We propose input and output scores to characterize and locate these types of features, and show that high values for both scores rarely co-occur in the same features.These findings have practical implications: after filtering out features with low output scores, we obtain 2-3x improvements when steering with SAEs, making them competitive with supervised methods. 1

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.013
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.010
Threshold uncertainty score0.033

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.013
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0020.003
Open science0.0010.002
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0100.009

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.003
GPT teacher head0.196
Teacher spread0.193 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicVehicle Dynamics and Control SystemsFrench-language works237,207