© 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 · 19-RESID-POST-AA · 103580 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
19-RESID-POST-AA
103580

INDEX

Explanations

Plural and singular

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_19/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

 three

-0.08

 drie

-0.08

 réunions

-0.08

 then

-0.08

 reuniões

-0.08

 kolme

-0.08

 ಮೂರು

-0.08

олож

-0.07

 trois

-0.07

 mbola

-0.07

POSITIVE LOGITS

_plural

0.13

Plural

0.13

 plural

0.13

plural

0.12

 Singular

0.12

 singular

0.12

 plurality

0.11

単

0.10

_MULT

0.10

 overwhelmingly

0.10

Activations Density 0.001%

No Known Activations