© 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. 22139
    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
     aika
    -0.07
     owed
    -0.07
     supplémentaires
    -0.07
     incorrectly
    -0.07
     જીત
    -0.07
     başarı
    -0.07
     errone
    -0.07
     Additional
    -0.07
     Brock
    -0.07
     vitória
    -0.06
    POSITIVE LOGITS
     meaningful
    0.25
     descriptive
    0.22
     distinctive
    0.21
     duidelijke
    0.20
     memorable
    0.19
     واضحة
    0.17
     intuitive
    0.17
     catchy
    0.17
     informative
    0.17
     evoc
    0.16
    Activations Density 0.020%

    No Known Activations