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. 43437
    Prev
    Next
    INDEX
    Explanations

    fruit

    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
     brainstorm
    -0.08
    routine
    -0.08
    aml
    -0.07
    .bill
    -0.07
    .twitter
    -0.07
     מתק
    -0.07
    apas
    -0.07
    espresso
    -0.07
    424
    -0.07
    ön
    -0.07
    POSITIVE LOGITS
     Влад
    0.09
    ński
    0.09
     Rouge
    0.08
    _indexes
    0.08
     डिस
    0.08
     īpa
    0.08
     ironically
    0.08
     номер
    0.08
    어난
    0.07
     നമ്പ
    0.07
    Activations Density 0.001%

    No Known Activations