© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54355
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     Gem
    -0.08
     прият
    -0.08
    جير
    -0.07
     inscritos
    -0.07
     cuyos
    -0.07
     introd
    -0.07
     Cous
    -0.07
     Martial
    -0.07
    рош
    -0.07
    -अ
    -0.07
    POSITIVE LOGITS
     I'd
    0.11
     i'd
    0.10
    Personally
    0.10
     myself
    0.10
     personally
    0.10
     Personally
    0.09
     הייתי
    0.09
     હું
    0.09
     предпоч
    0.09
     עצמי
    0.09
    Activations Density 0.087%

    No Known Activations