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. 111809
    Prev
    Next
    INDEX
    Explanations

    enzymes

    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
    HAR
    -0.09
    .addr
    -0.08
     પોલીસ
    -0.08
    addr
    -0.08
     lavage
    -0.08
    (non
    -0.08
    টু
    -0.08
     જોઈ
    -0.07
    (cols
    -0.07
     мок
    -0.07
    POSITIVE LOGITS
     संचालन
    0.08
     चाल
    0.08
    matige
    0.08
     impli
    0.08
    步骤
    0.08
     enzymes
    0.08
     housing
    0.08
    623
    0.08
     guided
    0.08
     провед
    0.08
    Activations Density 0.003%

    No Known Activations