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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130912
    Prev
    Next
    INDEX
    Explanations

    :/

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dénon
    -0.09
     hoor
    -0.09
    նար
    -0.08
    нит
    -0.08
    נסים
    -0.08
    દાવ
    -0.08
     Ft
    -0.08
     Previd
    -0.08
     MOB
    -0.08
    “M
    -0.08
    POSITIVE LOGITS
    regions
    0.09
    st
    0.09
    -reg
    0.08
    22
    0.08
    ul
    0.08
    str
    0.08
    -main
    0.08
    re
    0.08
    restricted
    0.08
    .re
    0.08
    Activations Density 0.001%

    No Known Activations