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. 98237
    Prev
    Next
    INDEX
    Explanations

    make

    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
    _operations
    -0.09
     Operations
    -0.09
     उज
    -0.08
    uppercase
    -0.08
    /buttons
    -0.08
     operations
    -0.08
    cod
    -0.08
     submitted
    -0.08
    operations
    -0.08
     uppercase
    -0.07
    POSITIVE LOGITS
     التقلي
    0.08
     dipercaya
    0.08
     traditionnelle
    0.08
    传统
    0.08
     DY
    0.08
     traditionnel
    0.08
     altru
    0.08
     تقری
    0.07
     یک
    0.07
     тради
    0.07
    Activations Density 0.066%

    No Known Activations