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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 162
    Prev
    Next
    INDEX
    Explanations

    ANDING

    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
    .mail
    -0.09
    uré
    -0.08
    _mail
    -0.08
    hurst
    -0.08
    mail
    -0.08
    ured
    -0.07
    Speak
    -0.07
    ervo
    -0.07
     মোট
    -0.07
    quarter
    -0.07
    POSITIVE LOGITS
    _CONNECTED
    0.08
     '{{
    0.08
    quets
    0.07
    -END
    0.07
     same
    0.07
    кат
    0.07
     ўжо
    0.07
    قدمة
    0.07
     ACK
    0.07
     ле
    0.07
    Activations Density 0.001%

    No Known Activations