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. 12145
    Prev
    Next
    INDEX
    Explanations

    Vitamin B12

    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
    Them
    -0.09
     ajustes
    -0.09
    -script
    -0.08
     ajuste
    -0.08
     武
    -0.08
     adjectives
    -0.08
     adjust
    -0.08
     louder
    -0.08
    -crafted
    -0.08
     emo
    -0.07
    POSITIVE LOGITS
    verkehr
    0.08
    Expired
    0.08
    ERR
    0.08
    .Memory
    0.08
     beachten
    0.08
    expired
    0.08
    dependent
    0.07
     oziroma
    0.07
     beroemde
    0.07
    (ticket
    0.07
    Activations Density 0.002%

    No Known Activations