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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 48175
    Prev
    Next
    INDEX
    Explanations

    sparkling

    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
    _logging
    -0.08
    нав
    -0.07
     nghiệp
    -0.07
    avigation
    -0.07
     자
    -0.07
     Visible
    -0.07
    visible
    -0.07
     riesgos
    -0.07
     horarios
    -0.07
     cited
    -0.07
    POSITIVE LOGITS
     उम
    0.08
     festive
    0.08
     الماء
    0.08
     counc
    0.08
    لىرى
    0.08
     ballot
    0.08
     gelungen
    0.08
    ples
    0.07
    、省
    0.07
     Conseil
    0.07
    Activations Density 0.001%

    No Known Activations