Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 119934
    Prev
    Next
    INDEX
    Explanations

    motivation, principles, quotes

    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
    Renew
    -0.09
    openhagen
    -0.08
    ´・
    -0.08
    atea
    -0.08
    زاب
    -0.08
    園
    -0.08
     teda
    -0.08
    ४
    -0.08
    改
    -0.08
    १३
    -0.08
    POSITIVE LOGITS
     αύ
    0.09
     필요한
    0.08
     автомобиль
    0.08
    ouf
    0.07
     rectangular
    0.07
     자동차
    0.07
     рисун
    0.07
     car
    0.07
     зарегистр
    0.07
     데이터를
    0.07
    Activations Density 0.000%

    No Known Activations