© 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. 30441
    Prev
    Next
    INDEX
    Explanations

    Arrow

    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
     insanity
    -0.09
     hend
    -0.08
     Carol
    -0.08
     Terry
    -0.08
    ें
    -0.07
     Airline
    -0.07
    ذهب
    -0.07
     Mont
    -0.07
     eder
    -0.07
     indent
    -0.07
    POSITIVE LOGITS
     improvement
    0.07
     Improvement
    0.07
     hopefully
    0.07
     kaupung
    0.07
     noqa
    0.07
     carr
    0.07
     ɔ
    0.07
     корист
    0.07
     inciso
    0.07
     nzvimbo
    0.07
    Activations Density 0.001%

    No Known Activations