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. 77878
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    heres
    -0.09
     Giant
    -0.07
     verbre
    -0.07
     admite
    -0.07
    .Program
    -0.07
     Ventures
    -0.07
     Kant
    -0.07
    gies
    -0.07
     Hom
    -0.07
     Nijmegen
    -0.07
    POSITIVE LOGITS
    .pattern
    0.08
    я
    0.07
     convenience
    0.07
    ając
    0.07
    notation
    0.07
     spr
    0.07
     tanke
    0.07
     தொட
    0.07
    .authentication
    0.07
     neurolog
    0.07
    Activations Density 0.021%

    No Known Activations