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. 60944
    Prev
    Next
    INDEX
    Explanations

    Safety steel-toe equipment

    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
     relieved
    -0.08
    Barcelona
    -0.08
    期限
    -0.08
     Relief
    -0.08
    AGEMENT
    -0.08
    mbio
    -0.08
     Peugeot
    -0.08
    ambio
    -0.08
     Barcelona
    -0.08
     Cameroon
    -0.08
    POSITIVE LOGITS
    usumik
    0.09
     ноги
    0.08
     açısından
    0.08
     Sonn
    0.08
    enek
    0.07
     inherent
    0.07
    attention
    0.07
     slippers
    0.07
     প্রতি
    0.07
     visage
    0.07
    Activations Density 0.011%

    No Known Activations