© 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. 51115
    Prev
    Next
    INDEX
    Explanations

    Medical emergencies

    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
    92
    -0.08
    ab
    -0.07
    东
    -0.07
    iab
    -0.07
    xcc
    -0.07
    xff
    -0.07
    现场
    -0.07
    致
    -0.07
    uples
    -0.07
    lett
    -0.07
    POSITIVE LOGITS
     ಹಣ
    0.08
    目です
    0.08
     *>(
    0.08
    kania
    0.08
     ಚಾಲ
    0.08
     OL
    0.07
     üzerine
    0.07
    "user
    0.07
     مجاني
    0.07
     ukukh
    0.07
    Activations Density 0.009%

    No Known Activations