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. 58616
    Prev
    Next
    INDEX
    Explanations

    light/solar energy

    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
     Eagle
    -0.08
     indices
    -0.08
    lož
    -0.08
     करव
    -0.08
     Đồng
    -0.07
     Rope
    -0.07
    кости
    -0.07
     índices
    -0.07
     mpl
    -0.07
     Index
    -0.07
    POSITIVE LOGITS
    Preferred
    0.08
    ,将
    0.08
    Lever
    0.08
    Fav
    0.08
    野
    0.08
     свет
    0.08
     flashes
    0.08
    Harness
    0.08
    Arthur
    0.08
     sunlight
    0.08
    Activations Density 0.002%

    No Known Activations