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. 13011
    Prev
    Next
    INDEX
    Explanations

    that

    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
    ांच्या
    -0.08
     विन
    -0.08
    須
    -0.08
     เป็น
    -0.08
     Toda
    -0.08
    則
    -0.08
    నున్న
    -0.07
    ields
    -0.07
     явля
    -0.07
     Polsce
    -0.07
    POSITIVE LOGITS
     pesky
    0.12
     elusive
    0.09
     intangible
    0.08
     pata
    0.08
    绿色
    0.08
     catchy
    0.08
     funnel
    0.08
     moss
    0.07
     coveted
    0.07
     Creek
    0.07
    Activations Density 0.055%

    No Known Activations