© 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. 23-RESID-POST-AA
    11. 49422
    Prev
    Next
    INDEX
    Explanations

    请

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ，可
    -0.09
    ,is
    -0.09
     are
    -0.09
     is
    -0.09
    ,no
    -0.08
     adalah
    -0.08
     komanso
    -0.08
    嗎
    -0.08
     pilihan
    -0.08
    zcan
    -0.08
    POSITIVE LOGITS
    勿
    0.13
    问
    0.12
    您
    0.12
    根据
    0.11
    牢记
    0.11
    注明
    0.11
    用
    0.11
    结合
    0.11
    确保
    0.10
    你
    0.10
    Activations Density 0.007%

    No Known Activations