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. 44249
    Prev
    Next
    INDEX
    Explanations

    FI

    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
    Ć
    -0.09
     athletes
    -0.08
     Jezus
    -0.08
    ಿಗಳ
    -0.08
     judic
    -0.07
    .chat
    -0.07
     участ
    -0.07
    acité
    -0.07
    INCT
    -0.07
     влас
    -0.07
    POSITIVE LOGITS
    模块
    0.09
    _MODULE
    0.08
     വിഭാഗ
    0.08
     módulos
    0.08
     módulo
    0.08
     Module
    0.07
    gradu
    0.07
     പ്രവർത്ത
    0.07
    म्म
    0.07
     module
    0.07
    Activations Density 0.008%

    No Known Activations