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. 12072
    Prev
    Next
    INDEX
    Explanations

    double

    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
     sac
    -0.07
     Dont
    -0.07
     paving
    -0.07
     TEN
    -0.07
     wak
    -0.07
     paved
    -0.07
     Sund
    -0.07
     pandemic
    -0.07
     Kale
    -0.07
    .geo
    -0.07
    POSITIVE LOGITS
    0.08
    把
    0.08
     Breakdown
    0.07
    骤
    0.07
     привед
    0.07
    bruch
    0.07
     Flyer
    0.07
    詳
    0.07
    ине
    0.07
     importantly
    0.07
    Activations Density 0.014%

    No Known Activations