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. 106261
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
    -faire
    -0.08
     רש
    -0.08
     belonged
    -0.08
     Nets
    -0.08
     итоге
    -0.08
    ాలలో
    -0.08
    -cü
    -0.08
    러운
    -0.08
    -0.07
     ő
    -0.07
    POSITIVE LOGITS
     projet
    0.08
    Secret
    0.08
     religiosa
    0.07
     noqon
    0.07
     Kaw
    0.07
    вад
    0.07
    start
    0.07
     gine
    0.07
    parameter
    0.07
    Saudi
    0.07
    Activations Density 0.024%

    No Known Activations