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. 112120
    Prev
    Next
    INDEX
    Explanations

    help

    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
    udar
    -0.08
     `'
    -0.07
    Indexed
    -0.07
     stev
    -0.07
     Indexed
    -0.07
    .s
    -0.07
    ្ប
    -0.07
     бан
    -0.07
    House
    -0.07
     Kama
    -0.07
    POSITIVE LOGITS
    困
    0.08
     divine
    0.08
     desesper
    0.08
     yardım
    0.08
     लेकर
    0.08
    ious
    0.08
    救
    0.08
    iously
    0.08
     desperate
    0.08
     plight
    0.08
    Activations Density 0.011%

    No Known Activations