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. 15-RESID-POST-AA
    6. 19386
    Prev
    Next
    INDEX
    Explanations

    simplification

    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
    ს
    -0.09
     ตาม
    -0.08
     срок
    -0.08
     bụla
    -0.08
     gerekir
    -0.08
     словно
    -0.08
     เพื่อ
    -0.08
     zabez
    -0.08
     Sä
    -0.08
    облем
    -0.08
    POSITIVE LOGITS
    Instead
    0.09
    网页版
    0.09
     virtualization
    0.09
     minimalist
    0.09
     modular
    0.09
     smaller
    0.08
     대신
    0.08
     streamlined
    0.08
     abbreviated
    0.08
    采用
    0.08
    Activations Density 0.042%

    No Known Activations