© 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. 44765
    Prev
    Next
    INDEX
    Explanations

    float

    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
     있음
    -0.09
    Battery
    -0.08
     diaria
    -0.08
    battery
    -0.08
    yt
    -0.08
    -lasting
    -0.08
    _______________
    -0.08
    _en
    -0.08
     battery
    -0.08
    -left
    -0.08
    POSITIVE LOGITS
     Hector
    0.08
     dialect
    0.08
     très
    0.07
    ограмм
    0.07
    елов
    0.07
    వ
    0.07
    \Support
    0.07
     Regard
    0.07
    .instrument
    0.07
    色情
    0.07
    Activations Density 0.000%

    No Known Activations