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. 60323
    Prev
    Next
    INDEX
    Explanations

    Math/logic problems

    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
    wira
    -0.08
     converting
    -0.07
    ärten
    -0.07
     Conversion
    -0.07
     aplicado
    -0.07
    mlich
    -0.07
    ूर्ण
    -0.07
     leveraging
    -0.07
     taxas
    -0.07
     "));↵
    -0.07
    POSITIVE LOGITS
     оны
    0.09
     slot
    0.08
    .slot
    0.08
    _slot
    0.08
     correspondiente
    0.08
    第五
    0.08
     KC
    0.08
    _FLAG
    0.08
     anterior
    0.08
     Venet
    0.08
    Activations Density 0.138%

    No Known Activations