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. 65786
    Prev
    Next
    INDEX
    Explanations

    of

    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
     imposs
    -0.08
    Germany
    -0.08
    planning
    -0.07
    PAC
    -0.07
    _NOP
    -0.07
     অ
    -0.07
    marked
    -0.07
    CONS
    -0.07
    ढ
    -0.07
    Graduate
    -0.07
    POSITIVE LOGITS
    vare
    0.08
     Reifen
    0.08
     epsilon
    0.07
     Pier
    0.07
     ω
    0.07
     slopes
    0.07
     resíduos
    0.07
     subsidies
    0.07
     transverse
    0.07
    öz
    0.07
    Activations Density 0.011%

    No Known Activations