© 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. 11-RESID-POST-AA
    11. 108486
    Prev
    Next
    INDEX
    Explanations

    hypothalamus

    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
    /conf
    -0.08
     mə
    -0.08
     kk
    -0.08
     Ê
    -0.07
    -minded
    -0.07
     Quebec
    -0.07
     minded
    -0.07
    -handed
    -0.07
     Indoor
    -0.07
    .conf
    -0.07
    POSITIVE LOGITS
     telefoon
    0.08
    ாப்ப
    0.07
     பள்ள
    0.07
     restroom
    0.07
     நடத்த
    0.07
    ந
    0.07
     отоп
    0.07
     Hamas
    0.07
    მა
    0.07
    Subjects
    0.07
    Activations Density 0.001%

    No Known Activations