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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11781
    Prev
    Next
    INDEX
    Explanations

    code dealing with data structures

    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
    adomo
    -0.08
    ouna
    -0.08
     поверхность
    -0.08
     distribución
    -0.07
     распредел
    -0.07
    wain
    -0.07
    occo
    -0.07
    _sd
    -0.07
     cubierta
    -0.07
    Clamp
    -0.07
    POSITIVE LOGITS
     Avoid
    0.08
     超
    0.07
    ↵
    0.07
     सुपर
    0.07
     Super
    0.07
     acusado
    0.07
     Felipe
    0.07
     Differ
    0.07
     αποφ
    0.07
     مام
    0.07
    Activations Density 0.003%

    No Known Activations