© 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. 19255
    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
     verzamelen
    -0.09
     sèlman
    -0.09
     verzam
    -0.09
     tikai
    -0.09
    ,max
    -0.09
     मात्रै
    -0.09
     ratios
    -0.09
     միայն
    -0.08
    >|
    -0.08
    .max
    -0.08
    POSITIVE LOGITS
    曜日
    0.14
     Thursday
    0.14
     सोमवार
    0.14
     weekday
    0.14
     Wednesday
    0.14
     Monday
    0.13
     Tuesday
    0.13
     रविवार
    0.13
     Thursdays
    0.13
    Thursday
    0.13
    Activations Density 0.009%

    No Known Activations