© 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. 20148
    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
     很
    -0.09
    实际上
    -0.09
     的
    -0.09
     څه
    -0.09
     somehow
    -0.09
     நாம்
    -0.09
    什么意思
    -0.09
     நான்
    -0.09
     WITHOUT
    -0.09
     цього
    -0.09
    POSITIVE LOGITS
     etc
    0.11
    、、
    0.10
     illetve
    0.10
     различные
    0.10
     valamint
    0.10
     various
    0.10
     например
    0.09
    、
    0.09
     сондай
    0.09
    ?,?,
    0.09
    Activations Density 0.346%

    No Known Activations