© 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. 64442
    Prev
    Next
    INDEX
    Explanations

    outsmarting, cleverness

    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
     correto
    -0.08
     voluntary
    -0.08
     influencia
    -0.08
    刊
    -0.08
     préciser
    -0.07
     automatic
    -0.07
     तुल
    -0.07
    خبار
    -0.07
    Normalized
    -0.07
    وضح
    -0.07
    POSITIVE LOGITS
     хозяй
    0.09
     સપ
    0.08
     જીત
    0.08
     camer
    0.08
    fulness
    0.08
     tactics
    0.08
     Spartan
    0.08
    路线
    0.08
     crafty
    0.07
     હત
    0.07
    Activations Density 0.012%

    No Known Activations