© 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. 21822
    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
    退出
    -0.10
    終了
    -0.09
     vandal
    -0.09
    waż
    -0.09
     nyuma
    -0.09
     izgub
    -0.09
     završ
    -0.08
    注销
    -0.08
     extingu
    -0.08
     öld
    -0.08
    POSITIVE LOGITS
     начинают
    0.10
     시작
    0.10
     commencent
    0.10
    .begin
    0.10
    begin
    0.09
     להתח
    0.09
    .Begin
    0.09
    ริ่ม
    0.09
     beginning
    0.09
    :start
    0.09
    Activations Density 0.013%

    No Known Activations