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. 43925
    Prev
    Next
    INDEX
    Explanations

    :

    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
     substantial
    -0.09
     भर
    -0.08
     تس
    -0.08
    'nin
    -0.08
     ज्यादा
    -0.07
     लगाए
    -0.07
    658
    -0.07
     sizable
    -0.07
    968
    -0.07
     Modular
    -0.07
    POSITIVE LOGITS
    lots
    0.09
     કંઈ
    0.09
     Csv
    0.08
    	output
    0.08
    something
    0.08
     эпох
    0.08
    output
    0.08
    格式
    0.08
     толькі
    0.08
    ഒരു
    0.08
    Activations Density 0.018%

    No Known Activations