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. 111863
    Prev
    Next
    INDEX
    Explanations

    Guru

    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
     event
    -0.08
    lify
    -0.07
    -0.07
     Daphne
    -0.07
     jaki
    -0.07
     Elast
    -0.07
     morir
    -0.07
     Mari
    -0.07
     CL
    -0.07
    event
    -0.07
    POSITIVE LOGITS
     contraire
    0.08
     numero
    0.08
     Nikol
    0.08
     successive
    0.08
     tenter
    0.08
     действует
    0.08
    0.08
     നമ്പ
    0.07
    님의
    0.07
     கட்ட
    0.07
    Activations Density 0.001%

    No Known Activations