© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44920
    Prev
    Next
    INDEX
    Explanations

    answering questions

    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
    Calculator
    -0.08
     determining
    -0.08
     computed
    -0.08
    compute
    -0.08
    find
    -0.07
     résoudre
    -0.07
    स्थान
    -0.07
    solve
    -0.07
    .find
    -0.07
    Solver
    -0.07
    POSITIVE LOGITS
    强调
    0.12
     강조
    0.11
     overly
    0.10
    כמה
    0.09
     emphas
    0.09
     vague
    0.09
    欧美
    0.08
     misguided
    0.08
     aborda
    0.08
    理念
    0.08
    Activations Density 0.059%

    No Known Activations