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. 102839
    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
    ipay
    -0.08
     configurations
    -0.08
    achadh
    -0.08
    /plugins
    -0.08
     rotating
    -0.08
     Pret
    -0.08
    .Objects
    -0.07
     Tse
    -0.07
     revenge
    -0.07
     soh
    -0.07
    POSITIVE LOGITS
    Subdivision
    0.13
     subdivision
    0.11
     subdivisions
    0.10
     Approx
    0.10
     refine
    0.10
    Approx
    0.10
     approximate
    0.10
    Bounding
    0.10
     Bounds
    0.10
    .bounds
    0.10
    Activations Density 0.026%

    No Known Activations