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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 117328
    Prev
    Next
    INDEX
    Explanations

    Math calculations with numbers

    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
     يق
    -0.08
    ুলি
    -0.08
    HAV
    -0.08
    YLE
    -0.07
    Essay
    -0.07
    Psych
    -0.07
     gezocht
    -0.07
     accompanies
    -0.07
    HAM
    -0.07
    YOffset
    -0.07
    POSITIVE LOGITS
     Vale
    0.09
    ното
    0.08
     dosing
    0.07
    ния
    0.07
     المطل
    0.07
     Angebot
    0.07
    தால்
    0.07
     Royaume
    0.07
     नाही
    0.07
     Vin
    0.07
    Activations Density 0.044%

    No Known Activations