© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 17930
    Prev
    Next
    INDEX
    Explanations

    Handling

    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
    Negative Logits
    leted
    -0.08
    _used
    -0.08
     ಮಾಡಿದ
    -0.08
    Unused
    -0.08
     منتخب
    -0.07
     USED
    -0.07
    quired
    -0.07
    used
    -0.07
     unused
    -0.07
     жасап
    -0.07
    POSITIVE LOGITS
     handling
    0.26
     처리
    0.24
    Handling
    0.23
     Handling
    0.23
    处理
    0.22
     handled
    0.20
     xử
    0.20
    扱
    0.19
    處
    0.19
     التعامل
    0.19
    Activations Density 0.094%

    No Known Activations