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. 52980
    Prev
    Next
    INDEX
    Explanations

    decimal

    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
     hoạch
    -0.08
     coag
    -0.08
     harvesting
    -0.07
     harvested
    -0.07
     Kä
    -0.07
     mange
    -0.07
     Journal
    -0.07
     seda
    -0.07
    -0.07
     studying
    -0.07
    POSITIVE LOGITS
     النات
    0.09
     ambiguous
    0.09
     Wendy
    0.08
    Egypt
    0.08
     दश
    0.08
    spell
    0.08
    .personal
    0.08
     无限
    0.08
     Gat
    0.08
    Infinity
    0.08
    Activations Density 0.015%

    No Known Activations