© 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. 21883
    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
     cómo
    -0.10
     how
    -0.09
     hvordan
    -0.09
     dicen
    -0.08
     hvernig
    -0.08
     πως
    -0.08
     bagaimana
    -0.08
    事情
    -0.08
     sagt
    -0.08
     một
    -0.08
    POSITIVE LOGITS
     of
    0.09
    .There
    0.09
    .↵
    0.08
     của
    0.08
    ankind
    0.08
    ().↵
    0.08
    of
    0.08
     ntawm
    0.08
    出的
    0.08
    ของ
    0.08
    Activations Density 0.008%

    No Known Activations