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. 58626
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     augmented
    -0.07
     سب
    -0.07
     سبک
    -0.07
    okon
    -0.07
    iri
    -0.07
     ingredient
    -0.07
    效率
    -0.07
     aug
    -0.07
    ıc
    -0.06
     ingrédients
    -0.06
    POSITIVE LOGITS
     siblings
    0.12
     sibling
    0.11
     filha
    0.10
     daughters
    0.10
     grandchildren
    0.09
     retali
    0.09
    Sibling
    0.09
     daughter
    0.09
    兄
    0.09
    Children
    0.09
    Activations Density 0.044%

    No Known Activations