© 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. 20892
    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
     инфекции
    -0.08
     болезни
    -0.08
     본
    -0.08
     個
    -0.08
     Generalitat
    -0.07
    odiac
    -0.07
     Vá
    -0.07
     entidad
    -0.07
     Pili
    -0.07
     Hafen
    -0.07
    POSITIVE LOGITS
     this
    0.08
    []
    0.08
     certain
    0.08
     Some
    0.08
     voorzichtig
    0.08
    នេះ
    0.08
     diesem
    0.08
     particular
    0.08
    Some
    0.07
    Certain
    0.07
    Activations Density 0.000%

    No Known Activations