Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12985
    Prev
    Next
    INDEX
    Explanations

    cars

    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
    .In
    -0.07
    };
    ↵
    ↵
    -0.07
     ਕਿਸ
    -0.07
    ேர
    -0.07
    (configuration
    -0.07
     Americana
    -0.07
     طال
    -0.07
     ਹ
    -0.07
     σαν
    -0.07
     comes
    -0.07
    POSITIVE LOGITS
    ifice
    0.08
     dilem
    0.07
    .fp
    0.07
    ỷ
    0.07
     squ
    0.07
    0.07
    quipe
    0.07
    გ
    0.07
    ¨
    0.07
    voke
    0.07
    Activations Density 0.001%

    No Known Activations