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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19305
    Prev
    Next
    INDEX
    Explanations

    graph theory

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deeper
    -0.07
    深入
    -0.07
    深
    -0.07
    $core
    -0.07
    ;↵
    -0.07
     इसे
    -0.07
     tanto
    -0.07
    .bar
    -0.07
    .rich
    -0.07
    .ck
    -0.07
    POSITIVE LOGITS
     য
    0.09
     Ո
    0.09
    >.
    0.08
     أج
    0.08
    leh
    0.08
    -employed
    0.08
     Ժ
    0.08
    ၃
    0.08
    gehör
    0.08
    acular
    0.08
    Activations Density 0.045%

    No Known Activations