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. 60358
    Prev
    Next
    INDEX
    Explanations

    10

    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
     gau
    -0.08
     varsity
    -0.08
     win
    -0.07
     ironing
    -0.07
     photographed
    -0.07
    ("***
    -0.07
     Gau
    -0.07
     Bry
    -0.07
    печ
    -0.07
     income
    -0.07
    POSITIVE LOGITS
    TG
    0.08
     απέ
    0.08
    Decimal
    0.08
    _decimal
    0.07
     kendaraan
    0.07
    UTF
    0.07
    Relative
    0.07
     toimii
    0.07
     kív
    0.07
     தேர
    0.07
    Activations Density 0.003%

    No Known Activations