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. 23-RESID-POST-AA
    6. 98361
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _requests
    -0.09
    Dp
    -0.08
     epic
    -0.08
    Requests
    -0.08
     elite
    -0.07
     crit
    -0.07
     fierce
    -0.07
    Df
    -0.07
     produtividade
    -0.07
    umnya
    -0.07
    POSITIVE LOGITS
    lelo
    0.08
    ular
    0.08
    arau
    0.08
    omer
    0.08
    iot
    0.08
    lip
    0.07
    cope
    0.07
     செயல
    0.07
     alyp
    0.07
    ותה
    0.07
    Activations Density 0.000%

    No Known Activations