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. 60861
    Prev
    Next
    INDEX
    Explanations

    random

    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
     zona
    -0.08
    čius
    -0.08
     Vis
    -0.08
     кож
    -0.07
    lint
    -0.07
    dagi
    -0.07
    ci
    -0.07
     Venus
    -0.07
     Andre
    -0.07
    驱
    -0.07
    POSITIVE LOGITS
    Scatter
    0.09
     Partido
    0.08
    ittle
    0.08
    tention
    0.08
    _IMPL
    0.07
    Pete
    0.07
    													
    0.07
     мн
    0.07
    struction
    0.07
     Scatter
    0.07
    Activations Density 0.001%

    No Known Activations