© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GPT-OSS-20B · 23-RESID-POST-AA · 5861 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
23-RESID-POST-AA
5861

INDEX

Explanations

circles and radii

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_23/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

ilibre

-0.09

 floors

-0.09

 Deutschmark

-0.09

 linux

-0.08

 Bahasa

-0.08

 magyar

-0.08

 trails

-0.08

agse

-0.08

 பகுத

-0.08

 அமைச்ச

-0.08

POSITIVE LOGITS

 circ

0.29

circ

0.24

 circum

0.23

 Circ

0.21

Circ

0.21

 circle

0.15

Radius

0.14

 radius

0.14

Circle

0.14

radius

0.13

Activations Density 0.080%

No Known Activations