© 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 EvalsExportsAPI 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. 20026
    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
    dart
    -0.10
     Dart
    -0.10
     penile
    -0.10
     dart
    -0.10
     Pakistan
    -0.09
     urinary
    -0.09
     bouts
    -0.09
     Kazakhstan
    -0.09
     Pakistani
    -0.09
    (widget
    -0.09
    POSITIVE LOGITS
     INDIRECT
    0.16
     TEXT
    0.15
     INDEX
    0.15
     SUBSTITUTE
    0.15
    TEXT
    0.13
     ROW
    0.13
     NETWORK
    0.13
     SUM
    0.13
     COUNT
    0.13
     VALUE
    0.13
    Activations Density 0.010%

    No Known Activations