© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45319
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hints
    -0.07
    所在
    -0.07
    最新
    -0.07
    此次
    -0.07
     لازم
    -0.07
    ావ
    -0.07
    社会
    -0.07
     Pats
    -0.07
    ogo
    -0.07
     दूर
    -0.07
    POSITIVE LOGITS
     modalidad
    0.09
    の場合
    0.09
    dt
    0.08
    டிய
    0.08
    Detached
    0.08
     modalidade
    0.08
     отличаются
    0.08
     mode
    0.08
     hingegen
    0.08
    ડ
    0.08
    Activations Density 0.093%

    No Known Activations