© 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. 20394
    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
     certain
    -0.08
     alcune
    -0.08
    Consider
    -0.07
     alcuni
    -0.07
    某
    -0.07
     unc
    -0.07
     algumas
    -0.07
    ülü
    -0.07
     некоторых
    -0.07
    ...),
    -0.07
    POSITIVE LOGITS
     glad
    0.21
     freut
    0.19
     horen
    0.17
    Glad
    0.16
     শুন
    0.16
     Glad
    0.15
     hören
    0.15
     hearing
    0.15
     hear
    0.15
     fico
    0.15
    Activations Density 0.012%

    No Known Activations