© 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. 11-RESID-POST-AA
    11. 63679
    Prev
    Next
    INDEX
    Explanations

    only matters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beg
    -0.09
     nueva
    -0.08
     diye
    -0.08
     Times
    -0.08
     rena
    -0.08
     नई
    -0.08
     recomendado
    -0.08
     naye
    -0.08
     DEVELOPMENT
    -0.08
     neues
    -0.08
    POSITIVE LOGITS
     unaffected
    0.10
     irrespective
    0.10
     regardless
    0.09
    ，却
    0.09
    Regardless
    0.08
     మాత్రమే
    0.08
     unor
    0.08
     essent
    0.08
    whether
    0.08
     seule
    0.08
    Activations Density 0.045%

    No Known Activations