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. 15-RESID-POST-AA
    6. 21
    Prev
    Next
    INDEX
    Explanations

    hyphen

    np_max-act-logits · gemini-2.0-flash

    hyphen

    np_max-act · claude-3-5-haiku-20241022Triggered by @kdearsty
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uttering
    -0.08
    ifying
    -0.08
    说道
    -0.08
    ków
    -0.08
    xiom
    -0.08
    caret
    -0.08
    appear
    -0.08
    cit
    -0.08
    plings
    -0.08
    arer
    -0.07
    POSITIVE LOGITS
     முழ
    0.13
    ովին
    0.12
     gamut
    0.12
    _full
    0.12
     الشاشة
    0.11
    -full
    0.11
     whole
    0.11
     full
    0.11
    .full
    0.11
     entière
    0.11
    Activations Density 0.006%

    No Known Activations