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. 131034
    Prev
    Next
    INDEX
    Explanations

    ter

    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
    _ref
    -0.08
     Ref
    -0.08
     estad
    -0.08
     ref
    -0.08
    olygon
    -0.07
    .ref
    -0.07
     umf
    -0.07
    _stat
    -0.07
     mast
    -0.07
     mike
    -0.07
    POSITIVE LOGITS
    bulas
    0.08
     bỏ
    0.07
    CHED
    0.07
    ্�
    0.07
     sə
    0.07
     федераль
    0.07
     bans
    0.07
    чэ
    0.07
    хий
    0.07
     faces
    0.07
    Activations Density 0.000%

    No Known Activations