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. 11779
    Prev
    Next
    INDEX
    Explanations

    comma and "and"

    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
     مها
    -0.08
     […]↵
    -0.08
     pag
    -0.08
     پرون
    -0.08
     nightmare
    -0.08
    匿名
    -0.08
    遭
    -0.08
     அல்லது
    -0.08
    。”↵
    -0.08
     ireo
    -0.08
    POSITIVE LOGITS
    👍
    0.09
    !!!
    0.09
    ek
    0.08
    wek
    0.08
    (res
    0.08
     superhero
    0.08
    llvm
    0.07
     announ
    0.07
     वीर
    0.07
     Champ
    0.07
    Activations Density 0.003%

    No Known Activations