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. 65951
    Prev
    Next
    INDEX
    Explanations

    Sprite

    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
    lenen
    -0.08
     myths
    -0.07
    BY
    -0.07
    _BUS
    -0.07
     ə
    -0.07
     обор
    -0.07
     ox
    -0.07
     yaxshi
    -0.07
    _REQ
    -0.07
    .when
    -0.07
    POSITIVE LOGITS
     सा
    0.08
    吾
    0.08
     Nano
    0.08
     Digi
    0.08
    (contents
    0.08
    截至
    0.08
     Fug
    0.08
    chị
    0.07
     Dew
    0.07
     Brace
    0.07
    Activations Density 0.001%

    No Known Activations