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. 12184
    Prev
    Next
    INDEX
    Explanations

    cartoon characters

    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
     POD
    -0.08
    Barn
    -0.08
    ១
    -0.08
     unspecified
    -0.07
     scarce
    -0.07
     -"
    -0.07
    函
    -0.07
    养老金
    -0.07
    esthesia
    -0.07
     PDO
    -0.07
    POSITIVE LOGITS
    聪
    0.09
     iconic
    0.08
     Leiter
    0.08
     ingenuity
    0.08
     goofy
    0.08
     Drake
    0.08
     فتاة
    0.08
     ninja
    0.07
     outr
    0.07
     девушек
    0.07
    Activations Density 0.018%

    No Known Activations