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. 11-RESID-POST-AA
    6. 76053
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     mbụ
    -0.08
     julọ
    -0.08
     하고
    -0.08
    -ob
    -0.08
     giving
    -0.07
    -ai
    -0.07
    ,也
    -0.07
    적으로
    -0.07
    viv
    -0.07
     hàng
    -0.07
    POSITIVE LOGITS
    /oder
    0.08
    lais
    0.08
     Alzheimer's
    0.08
     Sex
    0.07
     führt
    0.07
     Limb
    0.07
     ESPN
    0.07
    olf
    0.07
     ...)
    0.07
     nimmt
    0.07
    Activations Density 0.013%

    No Known Activations