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. 60897
    Prev
    Next
    INDEX
    Explanations

    yeast

    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
    يفون
    -0.08
     extraordinary
    -0.07
    ईल
    -0.07
    溪
    -0.07
     Questions
    -0.07
    ทุก
    -0.07
     ly
    -0.07
     washing
    -0.07
    ছিল
    -0.07
     Princip
    -0.07
    POSITIVE LOGITS
     bumps
    0.08
     BB
    0.08
    Birthday
    0.08
     간
    0.08
    dead
    0.08
    BB
    0.07
    brains
    0.07
    opt
    0.07
     JE
    0.07
    &
    0.07
    Activations Density 0.001%

    No Known Activations