© 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. 21525
    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
     prosperity
    -0.08
     shutil
    -0.08
    ,sizeof
    -0.08
    '})
    -0.07
    慢
    -0.07
    ;++
    -0.07
    -enh
    -0.07
    ❤
    -0.07
    ，两
    -0.07
    🙂
    -0.07
    POSITIVE LOGITS
     modulo
    0.09
     مواقع
    0.09
     נמצ
    0.09
     مسیر
    0.09
     gehören
    0.09
     either
    0.09
     Möglich
    0.09
     Fälle
    0.09
     Những
    0.09
     Να
    0.09
    Activations Density 0.016%

    No Known Activations