© 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. 19973
    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
     odnosno
    -0.11
     Можно
    -0.11
     Can
    -0.10
     Είναι
    -0.10
     možemo
    -0.10
     possiamo
    -0.10
     voidaan
    -0.10
     ويمكن
    -0.10
     অন্যান্য
    -0.10
     Մենք
    -0.10
    POSITIVE LOGITS
     then
    0.16
    ,
    0.11
     instead
    0.11
    Then
    0.11
    then
    0.10
    ،
    0.10
    ",
    0.10
     accordingly
    0.10
    ',
    0.10
     вместо
    0.10
    Activations Density 0.034%

    No Known Activations