© 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. 22431
    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
     discrepancy
    -0.09
     minimal
    -0.08
     their
    -0.07
     difference
    -0.07
     diagonal
    -0.07
    ేడ
    -0.07
     a
    -0.07
    inho
    -0.07
     =
    -0.07
     diag
    -0.07
    POSITIVE LOGITS
     条
    0.10
    条件
    0.10
     조건
    0.10
     Bedingungen
    0.10
    所有
    0.10
    >x
    0.10
    조건
    0.09
     شرط
    0.09
     elif
    0.09
     elsif
    0.09
    Activations Density 0.047%

    No Known Activations