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. 112114
    Prev
    Next
    INDEX
    Explanations

    Word

    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
     eyel
    -0.08
     Patriot
    -0.08
    Criterion
    -0.07
     enrolling
    -0.07
     idiot
    -0.07
     seques
    -0.07
    Tel
    -0.07
    เข้
    -0.07
     Irr
    -0.07
    яш
    -0.07
    POSITIVE LOGITS
     nouns
    0.11
    .words
    0.10
     words
    0.09
     Words
    0.09
     hashtags
    0.09
     frequency
    0.09
     الكلمات
    0.09
    频
    0.09
    Words
    0.09
    analysis
    0.09
    Activations Density 0.005%

    No Known Activations