© 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. 18512
    Prev
    Next
    INDEX
    Explanations

    Python code execution

    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
     };↵↵//
    -0.09
     സാധ്യത
    -0.09
     نجد
    -0.09
    (insert
    -0.09
     weergegeven
    -0.08
     مواجهة
    -0.08
     presenteren
    -0.08
     ارتفاع
    -0.08
    …..↵↵
    -0.08
     منطقة
    -0.08
    POSITIVE LOGITS
    EOF
    0.09
    E
    0.09
     etc
    0.08
    ;font
    0.08
     physics
    0.08
    JAVA
    0.08
     EOF
    0.08
    PY
    0.08
    #from
    0.08
    .tmp
    0.07
    Activations Density 0.000%

    No Known Activations