© 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. 19381
    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
     véritable
    -0.09
     либо
    -0.08
     réellement
    -0.08
     অথবা
    -0.08
     :↵
    -0.08
     daadwerkelijk
    -0.08
    ifter
    -0.08
     )↵
    -0.08
     vérit
    -0.08
     verdader
    -0.08
    POSITIVE LOGITS
     implies
    0.23
     suggests
    0.21
     indicates
    0.20
     implying
    0.18
     imply
    0.16
    意味着
    0.14
     suggest
    0.14
     indicating
    0.14
     Indicates
    0.14
     suggesting
    0.14
    Activations Density 0.055%

    No Known Activations