© 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. 68056
    Prev
    Next
    INDEX
    Explanations

    electrical power/formulas

    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
     exclusion
    -0.09
    911
    -0.08
    _HISTORY
    -0.08
     history
    -0.08
     exclusions
    -0.08
     Steck
    -0.08
    зу
    -0.08
    _predictions
    -0.08
    898
    -0.07
    _history
    -0.07
    POSITIVE LOGITS
     CFO
    0.09
     causado
    0.08
     Debit
    0.08
     ব্যাং
    0.08
     ঠিক
    0.08
     accrued
    0.08
     আমি
    0.08
    ্প
    0.08
     mér
    0.08
     debit
    0.08
    Activations Density 0.004%

    No Known Activations