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. 43945
    Prev
    Next
    INDEX
    Explanations

    congr

    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
    壮
    -0.08
     sv
    -0.07
     ч
    -0.07
    ВС
    -0.07
     nö
    -0.07
     দর্শ
    -0.07
     Ministry
    -0.07
     Meme
    -0.07
    oustic
    -0.07
    ющий
    -0.07
    POSITIVE LOGITS
     congr
    0.09
     modulo
    0.08
    事項
    0.08
    fix
    0.08
     Tall
    0.07
    Gre
    0.07
    Modulo
    0.07
     pli
    0.07
     computations
    0.07
     Bé
    0.07
    Activations Density 0.003%

    No Known Activations