© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GPT-OSS-20B · 23-RESID-POST-AA · 49178 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
23-RESID-POST-AA
49178

INDEX

Explanations

Resource

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

verlust

-0.09

 arrogance

-0.08

 geblieben

-0.08

 verniet

-0.08

成长

-0.08

 ascent

-0.08

 Integrity

-0.08

 corrupted

-0.07

 muerte

-0.07

 enri

-0.07

POSITIVE LOGITS

 allocation

0.28

配置

0.26

 Allocation

0.25

安排

0.25

allocation

0.25

Allocation

0.25

调

0.25

 scheduling

0.23

 allocations

0.23

調

0.22

Activations Density 0.084%

No Known Activations