Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43932
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
    -theme
    -0.07
    -0.07
     undergo
    -0.07
     संक्रमण
    -0.07
    耗
    -0.07
    ण
    -0.07
     recession
    -0.07
    ifference
    -0.07
     nerve
    -0.06
     motors
    -0.06
    POSITIVE LOGITS
     최초
    0.09
     первым
    0.09
     verð
    0.09
     თვით
    0.09
     старт
    0.09
     სიცოცხ
    0.09
    _www
    0.09
     ahau
    0.09
    후
    0.09
     japanese
    0.09
    Activations Density 0.011%

    No Known Activations