© 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. 683
    Prev
    Next
    INDEX
    Explanations

    of

    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
    itié
    -0.08
     merr
    -0.08
     prend
    -0.07
     suur
    -0.07
    iske
    -0.07
    そして
    -0.07
    /C
    -0.07
     junt
    -0.07
     CPI
    -0.07
     மற்றும்
    -0.07
    POSITIVE LOGITS
     названием
    0.08
    =name
    0.08
    ಿಯಲ್ಲಿ
    0.08
    ายใน
    0.08
    ಾನ
    0.08
     название
    0.07
     Pascal
    0.07
     pás
    0.07
    ಲೆಯಲ್ಲಿ
    0.07
    لز
    0.07
    Activations Density 0.002%

    No Known Activations