© 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. 23-RESID-POST-AA
    11. 50474
    Prev
    Next
    INDEX
    Explanations

    Sports coaches

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     аз
    -0.08
    	Message
    -0.08
    altet
    -0.08
    Message
    -0.08
    AZ
    -0.08
    ptious
    -0.08
    _Message
    -0.07
    Annotations
    -0.07
     للاست
    -0.07
     Message
    -0.07
    POSITIVE LOGITS
     eject
    0.08
    nehmer
    0.08
     filesystem
    0.07
     administer
    0.07
     Tub
    0.07
     edits
    0.07
     turbulence
    0.07
     આવતા
    0.07
     കാല
    0.07
     adjacency
    0.07
    Activations Density 0.001%

    No Known Activations