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. 60747
    Prev
    Next
    INDEX
    Explanations

    Tables or desks

    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
     FOX
    -0.08
    CBC
    -0.08
     entrant
    -0.08
     নেতা
    -0.08
    -aware
    -0.08
     Mange
    -0.07
     gec
    -0.07
     Lindsay
    -0.07
     उद
    -0.07
     proxies
    -0.07
    POSITIVE LOGITS
     countertops
    0.11
     countertop
    0.10
    manship
    0.08
    用品
    0.08
    上的
    0.08
     cockpit
    0.08
     поверхность
    0.08
     Dell
    0.08
    /shop
    0.08
    platten
    0.07
    Activations Density 0.019%

    No Known Activations