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. 77136
    Prev
    Next
    INDEX
    Explanations

    x

    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
    .utils
    -0.09
     Drum
    -0.08
     loves
    -0.08
    -0.08
     deputy
    -0.07
     medal
    -0.07
     drum
    -0.07
     charity
    -0.07
     mudou
    -0.07
     Stefano
    -0.07
    POSITIVE LOGITS
     идет
    0.08
     ನಡೆಯ
    0.08
     laden
    0.08
     /*!<
    0.08
    quelle
    0.08
    emento
    0.08
     आंक
    0.07
    umatoid
    0.07
     mettre
    0.07
    Quelle
    0.07
    Activations Density 0.112%

    No Known Activations