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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12739
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Kath
    -0.09
     древ
    -0.08
    Breadcrumb
    -0.08
     чек
    -0.08
     гориз
    -0.08
     Smith
    -0.08
     миров
    -0.07
     І
    -0.07
     खुल
    -0.07
     душе
    -0.07
    POSITIVE LOGITS
    amm
    0.08
    store
    0.08
    amo
    0.08
     acerca
    0.07
     store
    0.07
     flank
    0.07
     tray
    0.07
    GR
    0.07
    aktiv
    0.07
    .Fl
    0.07
    Activations Density 0.001%

    No Known Activations