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. 58556
    Prev
    Next
    INDEX
    Explanations

    Counting multiples

    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
     feathers
    -0.09
     ώ
    -0.08
    ारण
    -0.08
    त्त
    -0.07
    üllen
    -0.07
    .ok
    -0.07
     broth
    -0.07
     cheeks
    -0.07
     εξέ
    -0.07
     humility
    -0.07
    POSITIVE LOGITS
     divisible
    0.12
     gcd
    0.11
     intersection
    0.10
    Intersect
    0.10
     intersects
    0.10
     multiples
    0.09
    Intersection
    0.09
     intersections
    0.09
     intersect
    0.09
    intersection
    0.08
    Activations Density 0.030%

    No Known Activations