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. 44013
    Prev
    Next
    INDEX
    Explanations

    Preparing/cleaning shrimp

    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
    充分
    -0.08
    תגובה
    -0.08
     dich
    -0.07
    房
    -0.07
     Tex
    -0.07
     facture
    -0.07
    作品
    -0.07
     deten
    -0.07
    [,
    -0.07
    来也
    -0.07
    POSITIVE LOGITS
     ختم
    0.09
     Beginners
    0.08
    .Invalid
    0.08
     inutil
    0.08
     പി
    0.08
    świadc
    0.08
     للأطفال
    0.08
    GED
    0.07
     helicopter
    0.07
    mente
    0.07
    Activations Density 0.003%

    No Known Activations