© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 22195
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     პლ
    -0.09
     北京赛车开奖
    -0.09
     天天爱彩票提现
    -0.09
     krwar
    -0.09
    超碰
    -0.09
    变态另类
    -0.09
    ილების
    -0.09
    _久久爱
    -0.09
    ನವದೆಹಲಿ
    -0.09
     мәдәний
    -0.09
    POSITIVE LOGITS
    .
    0.12
    .This
    0.11
    에도
    0.11
    ،
    0.10
    .It
    0.10
    ؛
    0.10
    .They
    0.10
    .The
    0.10
    ,and
    0.10
    ,the
    0.10
    Activations Density 0.198%

    No Known Activations