© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18767
    Prev
    Next
    INDEX
    Explanations

    攻

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Argument
    -0.08
    -0.07
    Require
    -0.07
    -0.07
    player
    -0.07
     【
    -0.07
    worker
    -0.06
    within
    -0.06
    abag
    -0.06
    .require
    -0.06
    POSITIVE LOGITS
    期开奖结果
    0.10
    了一等奖
    0.10
    中奖了
    0.09
     vaike
    0.09
    'adresse
    0.09
    ому
    0.09
    lyni
    0.09
    елич
    0.09
    تمبر
    0.09
    exesha
    0.09
    Activations Density 0.000%
    No Known Activations