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. 54015
    Prev
    Next
    INDEX
    Explanations

    say

    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
     الموا
    -0.09
    Looks
    -0.07
     تسبب
    -0.07
     تبحث
    -0.07
    Blo
    -0.07
    olithic
    -0.07
     Blo
    -0.07
    ALLED
    -0.07
     amount
    -0.07
    chein
    -0.07
    POSITIVE LOGITS
    兄
    0.08
    姐妹
    0.08
    菜
    0.08
     persönlich
    0.07
     Seating
    0.07
     sisters
    0.07
     pessoal
    0.07
    daj
    0.07
     SEC
    0.07
     azy
    0.07
    Activations Density 0.012%

    No Known Activations