© 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. 21386
    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
     mineria
    -0.09
    ിന്റെ
    -0.09
    amalama
    -0.09
     կարելի
    -0.08
    യുടെ
    -0.08
     timbang
    -0.08
    croft
    -0.08
     קען
    -0.08
     америка
    -0.08
     америки
    -0.08
    POSITIVE LOGITS
    〜
    0.09
    .):
    0.08
    }-{
    0.08
     jede
    0.08
    σε
    0.08
    ）↵↵
    0.08
    ၁
    0.08
    〕
    0.08
     váš
    0.07
     sareng
    0.07
    Activations Density 0.002%

    No Known Activations