© 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. 19704
    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
    TRGL
    -0.09
    Además
    -0.09
    Однако
    -0.09
    Wenn
    -0.08
    Während
    -0.08
    Além
    -0.08
    *",
    -0.08
    Но
    -0.08
    __;↵
    -0.08
    ！↵↵↵
    -0.08
    POSITIVE LOGITS
     should
    0.18
     =
    0.17
     Provide
    0.15
     is
    0.15
     Should
    0.15
     是
    0.15
     يجب
    0.14
     must
    0.14
     will
    0.14
     என்பது
    0.13
    Activations Density 0.003%

    No Known Activations