Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44130
    Prev
    Next
    INDEX
    Explanations

    C++ header comments

    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
    惊
    -0.08
     extraordinary
    -0.08
    .Pageable
    -0.08
     entourage
    -0.08
    ům
    -0.07
     Amaz
    -0.07
     mají
    -0.07
    玛
    -0.07
     sanctions
    -0.07
     миров
    -0.07
    POSITIVE LOGITS
     deline
    0.07
    *******/↵
    0.07
    Lite
    0.07
     só
    0.07
    ecast
    0.07
     vision
    0.07
     coverage
    0.07
     chunks
    0.07
    0.07
     +:+
    0.07
    Activations Density 0.001%

    No Known Activations