© 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. 22335
    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
     Vendor
    -0.11
    配送
    -0.10
     वायर
    -0.10
     spam
    -0.09
     multer
    -0.09
     actuator
    -0.09
     diode
    -0.09
     onboarding
    -0.09
    美容
    -0.09
     vendor
    -0.09
    POSITIVE LOGITS
     historians
    0.34
     historical
    0.33
     histori
    0.32
    Historical
    0.32
     historian
    0.31
     Historical
    0.31
     역사
    0.29
     historischen
    0.29
     истор
    0.29
     تاریخی
    0.29
    Activations Density 0.184%

    No Known Activations