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. 56096
    Prev
    Next
    INDEX
    Explanations

    USA

    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
    Paragraph
    -0.09
    iante
    -0.08
    Young
    -0.08
    ontos
    -0.08
    .tex
    -0.08
    ividu
    -0.08
    Probability
    -0.07
    Ent
    -0.07
    application
    -0.07
    antes
    -0.07
    POSITIVE LOGITS
     workmanship
    0.10
     fabricación
    0.10
     craftsmanship
    0.10
    进口
    0.10
     تصنيع
    0.09
    采购
    0.09
     certification
    0.09
     kaufen
    0.09
     certified
    0.09
     Manufacturing
    0.09
    Activations Density 0.052%

    No Known Activations