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. 111740
    Prev
    Next
    INDEX
    Explanations

    math

    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
    èk
    -0.08
     Released
    -0.08
     ਇਕ
    -0.08
    ʻe
    -0.08
     voyager
    -0.08
     Outreach
    -0.08
     ज़
    -0.08
     kres
    -0.08
    た
    -0.07
     విడుదల
    -0.07
    POSITIVE LOGITS
    组合
    0.09
    Together
    0.09
    Comb
    0.08
     samlet
    0.08
    _comb
    0.08
     overall
    0.08
     juntos
    0.08
     comb
    0.08
     respectively
    0.08
    Таким
    0.08
    Activations Density 0.130%

    No Known Activations