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. 382
    Prev
    Next
    INDEX
    Explanations

    math 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
    Chest
    -0.08
     hospitalization
    -0.08
    Integration
    -0.08
    cliffe
    -0.08
    Passport
    -0.07
     Townsend
    -0.07
     poderosa
    -0.07
     DL
    -0.07
     Crosby
    -0.07
    implant
    -0.07
    POSITIVE LOGITS
     regardless
    0.08
     boils
    0.08
     divergent
    0.07
     irrespective
    0.07
     તમામ
    0.07
    活
    0.07
     unat
    0.07
    ડે
    0.07
     انگی
    0.07
     diversion
    0.07
    Activations Density 0.061%

    No Known Activations