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. 43191
    Prev
    Next
    INDEX
    Explanations

    heading

    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
    .jar
    -0.08
    uable
    -0.08
     Broker
    -0.08
    agus
    -0.08
    ave
    -0.08
    erv
    -0.08
     prostit
    -0.08
    .interceptor
    -0.08
     prostitution
    -0.08
    ujar
    -0.07
    POSITIVE LOGITS
     uppercase
    0.10
     accents
    0.09
     bold
    0.09
     teas
    0.09
     výraz
    0.09
     announcements
    0.09
    タイトル
    0.08
     headings
    0.08
     capitalization
    0.08
     عند
    0.08
    Activations Density 0.006%

    No Known Activations