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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69449
    Prev
    Next
    INDEX
    Explanations

    multiple choice questions/math

    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
    .serialize
    -0.08
    -0.07
     Params
    -0.07
     Types
    -0.07
     추진
    -0.07
     Sothe
    -0.07
     Admin
    -0.07
    ress
    -0.07
     SIG
    -0.07
     ราย
    -0.07
    POSITIVE LOGITS
    答案
    0.13
    哪个
    0.12
    哪
    0.10
    _answer
    0.10
    正确
    0.10
     answering
    0.10
     juiste
    0.10
     answers
    0.09
    找到
    0.09
    回答
    0.09
    Activations Density 0.068%
    No Known Activations