© 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. 21379
    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
     любую
    -0.13
     any
    -0.12
     любой
    -0.11
     любого
    -0.11
    任何
    -0.11
    (any
    -0.11
     любые
    -0.10
     любое
    -0.10
     qualquer
    -0.10
     orice
    -0.10
    POSITIVE LOGITS
     ciertos
    0.11
     constrained
    0.11
     bestimmten
    0.11
     nagyon
    0.11
     bardzo
    0.11
     extremely
    0.11
     ciertas
    0.10
     очень
    0.10
     kiosk
    0.10
    某
    0.10
    Activations Density 0.037%

    No Known Activations