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. 30648
    Prev
    Next
    INDEX
    Explanations

    race

    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
     ortam
    -0.08
     stakeholder
    -0.07
     caso
    -0.07
     Burton
    -0.07
     Mansfield
    -0.07
    աշ
    -0.07
    全文
    -0.07
    -0.07
    _DEL
    -0.07
     interdiscip
    -0.07
    POSITIVE LOGITS
    genoten
    0.09
     humana
    0.08
     humaine
    0.08
    Uns
    0.08
     mennesker
    0.08
    /type
    0.08
     sd
    0.08
    0.08
     daw
    0.08
    ினர்
    0.08
    Activations Density 0.020%

    No Known Activations