© 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. 11-RESID-POST-AA
    11. 113499
    Prev
    Next
    INDEX
    Explanations

    russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ospatial
    -0.10
    십시오
    -0.07
    थे
    -0.07
     sammen
    -0.07
     Camin
    -0.07
    ИХ
    -0.07
     aando
    -0.07
    -og
    -0.07
    тк
    -0.07
     који
    -0.07
    POSITIVE LOGITS
     уп
    0.09
     principales
    0.08
     noche
    0.08
    omis
    0.08
     מוט
    0.08
    LOYEE
    0.07
     embarrassing
    0.07
     vaj
    0.07
    quotes
    0.07
     measures
    0.07
    Activations Density 0.003%

    No Known Activations