© 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. 20534
    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
    -half
    -0.09
    -none
    -0.09
    رياض
    -0.08
    פורט
    -0.08
    /files
    -0.08
     misschien
    -0.08
    (empty
    -0.08
    (two
    -0.08
    -empty
    -0.08
    -maint
    -0.08
    POSITIVE LOGITS
     smaller
    0.12
     <
    0.12
     μικ
    0.11
     Smaller
    0.10
     küçük
    0.10
     <↵
    0.10
     rar
    0.10
     small
    0.09
     >
    0.09
     ചെറിയ
    0.09
    Activations Density 0.003%

    No Known Activations