© 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. 95361
    Prev
    Next
    INDEX
    Explanations

    Dates and time

    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
     haunting
    -0.09
     Charter
    -0.09
    /Text
    -0.08
     veit
    -0.08
    /Data
    -0.08
    lighet
    -0.08
     Fors
    -0.08
    оф
    -0.08
    oak
    -0.07
     Valk
    -0.07
    POSITIVE LOGITS
     telesc
    0.09
    改革
    0.08
    IBUTE
    0.07
     ಸ್ಥ
    0.07
     ऋ
    0.07
     ರೀತ
    0.07
     redundant
    0.07
     voluntarily
    0.07
     Miguel
    0.07
     pás
    0.07
    Activations Density 0.000%

    No Known Activations