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. 75973
    Prev
    Next
    INDEX
    Explanations

    ADHD

    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
     hữu
    -0.08
    �
    -0.08
    泄
    -0.08
     خطوات
    -0.07
     வரை
    -0.07
    पे
    -0.07
     melts
    -0.07
    売
    -0.07
    Erro
    -0.07
     stressing
    -0.07
    POSITIVE LOGITS
     cognitive
    0.08
    checkbox
    0.08
    🏼
    0.08
     medications
    0.08
     ISC
    0.08
     disorders
    0.08
     GEN
    0.08
     medication
    0.08
     Tribe
    0.07
     Meredith
    0.07
    Activations Density 0.002%

    No Known Activations