© 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. 18435
    Prev
    Next
    INDEX
    Explanations

    alert

    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
    奥
    -0.08
    ılmış
    -0.08
     нот
    -0.07
     shady
    -0.07
     fruct
    -0.07
     плен
    -0.07
     aner
    -0.07
     nota
    -0.07
     奥
    -0.07
     раст
    -0.07
    POSITIVE LOGITS
    _threshold
    0.14
     triggered
    0.13
    .threshold
    0.13
    Threshold
    0.13
     Threshold
    0.13
    Triggered
    0.13
     thresholds
    0.12
    (Alert
    0.12
    threshold
    0.12
    -trigger
    0.12
    Activations Density 0.011%

    No Known Activations