© 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. 112610
    Prev
    Next
    INDEX
    Explanations

    We

    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
     bouncing
    -0.08
     Health
    -0.08
     स्वास्थ्य
    -0.08
     profitez
    -0.08
    פורט
    -0.08
    covery
    -0.08
    arter
    -0.08
    rant
    -0.08
    観
    -0.08
     analiz
    -0.08
    POSITIVE LOGITS
    Sab
    0.08
     tricky
    0.08
    мента
    0.08
     трябва
    0.08
     Sab
    0.08
    Vz
    0.07
     SAB
    0.07
    Mand
    0.07
     لط
    0.07
    qn
    0.07
    Activations Density 0.038%

    No Known Activations