© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47219
    Prev
    Next
    INDEX
    Explanations

    1

    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
     mange
    -0.08
     nette
    -0.08
     significativamente
    -0.08
     déc
    -0.08
    很多
    -0.08
     divert
    -0.08
     reply
    -0.07
     dina
    -0.07
     generally
    -0.07
     полноцен
    -0.07
    POSITIVE LOGITS
     tal
    0.07
     Fib
    0.07
     Certificates
    0.07
     Shopper
    0.07
     Пос
    0.07
     Supported
    0.07
    contents
    0.07
    _locator
    0.07
     Prevention
    0.07
    checkpoint
    0.07
    Activations Density 0.004%

    No Known Activations