© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GPT-OSS-20B · 19-RESID-POST-AA · 23082 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
19-RESID-POST-AA
23082

INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0

Dataset (Dashboard)

Various

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

 будет

-0.09

Whatever

-0.09

 Various

-0.08

 various

-0.08

 will

-0.08

 Whatever

-0.08

 whatever

-0.08

 થશે

-0.08

 станет

-0.08

 lots

-0.08

POSITIVE LOGITS

 unless

0.13

unless

0.13

 Unless

0.12

 yleensä

0.12

 généralement

0.12

 doorga

0.12

 almeno

0.12

 meestal

0.11

Unless

0.11

usually

0.11

Activations Density 0.044%

No Known Activations