© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 103474
    Prev
    Next
    INDEX
    Explanations

    specify

    np_max-act-logits · gemini-2.0-flash
    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
     tatsäch
    -0.08
     daadwerk
    -0.08
     actual
    -0.07
    实际
    -0.07
     באמת
    -0.07
     réelle
    -0.07
    íguez
    -0.07
     entretenimiento
    -0.07
     ulaş
    -0.07
     Übersicht
    -0.07
    POSITIVE LOGITS
     specify
    0.29
     specifying
    0.29
     préciser
    0.28
    Specify
    0.27
     specifies
    0.27
     Specify
    0.26
     especific
    0.26
     spéc
    0.26
    指定
    0.26
     specified
    0.25
    Activations Density 0.157%

    No Known Activations