© 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. 21518
    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
     आदि
    -0.11
    ":↵↵
    -0.10
     etc
    -0.10
    ിശ
    -0.09
     વગેરે
    -0.09
    -0.09
    -adịghị
    -0.09
    -0.09
     mwingine
    -0.09
    ახლ
    -0.09
    POSITIVE LOGITS
    since
    0.14
     since
    0.13
     Since
    0.11
    ?
    0.11
     because
    0.10
    ，因为
    0.10
    Since
    0.10
    !
    0.10
     satisfy
    0.09
    ?(
    0.09
    Activations Density 0.022%
    No Known Activations