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. 112937
    Prev
    Next
    INDEX
    Explanations

    Arithmetic and differences

    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
    Cloud
    -0.08
     Whole
    -0.08
     بالت
    -0.08
     Governments
    -0.07
     inhibited
    -0.07
    koch
    -0.07
    True
    -0.07
    Whole
    -0.07
     sugars
    -0.07
    ***/↵
    -0.07
    POSITIVE LOGITS
    hit
    0.08
     Jason
    0.08
    .hit
    0.08
     dates
    0.07
     hit
    0.07
     azonban
    0.07
    ेव
    0.07
     SW
    0.07
    Jason
    0.07
    .Program
    0.07
    Activations Density 0.047%

    No Known Activations