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. 77568
    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
     ქს
    -0.10
     öý
    -0.08
     анк
    -0.08
     торрент
    -0.08
    ಿಕೆಟ್
    -0.08
     სახ
    -0.08
     presos
    -0.08
     ntab
    -0.08
     მედ
    -0.08
    ნა
    -0.08
    POSITIVE LOGITS
    0.09
     United
    0.07
    हरूले
    0.07
     AM
    0.07
     arrogant
    0.07
     сделал
    0.07
    _https
    0.07
     IFR
    0.07
     تو
    0.07
     Reach
    0.07
    Activations Density 0.007%

    No Known Activations