© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GPT-OSS-20B · 11-RESID-POST-AA · 111516 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
11-RESID-POST-AA
111516

INDEX

Explanations

Math formulas

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0

Dataset (Dashboard)

Various

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 operatie

-0.08

EVENT

-0.08

 operation

-0.08

 lean

-0.08

det

-0.07

 detached

-0.07

Preparation

-0.07

 kerja

-0.07

det

-0.07

 preparation

-0.07

POSITIVE LOGITS

_shortcode

0.10

هاية

0.09

 telesc

0.09

 disputed

0.08

umulative

0.08

 enkulu

0.08

elescope

0.08

 Série

0.08

 시즌

0.08

 Enquanto

0.08

Activations Density 0.040%

No Known Activations