Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19591
    Prev
    Next
    INDEX
    Explanations

    margin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    薦
    -0.09
     carefree
    -0.08
     communiquer
    -0.08
     moyens
    -0.08
     revolving
    -0.08
    ?!↵↵
    -0.07
    故
    -0.07
    μό
    -0.07
    psych
    -0.07
     communicated
    -0.07
    POSITIVE LOGITS
     tbody
    0.09
    -third
    0.08
    oms
    0.08
     colspan
    0.07
     صفحات
    0.07
     страниц
    0.07
     понадоб
    0.07
     deserve
    0.07
     eof
    0.07
    .sections
    0.07
    Activations Density 0.001%

    No Known Activations