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. 43246
    Prev
    Next
    INDEX
    Explanations

    period

    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
    avana
    -0.08
    fab
    -0.08
     spotlight
    -0.08
     lofty
    -0.08
     apro
    -0.08
     antib
    -0.08
    fname
    -0.07
     continua
    -0.07
     fakat
    -0.07
    ектора
    -0.07
    POSITIVE LOGITS
     Hare
    0.08
     کیا
    0.08
     ”↵↵
    0.07
    男女
    0.07
    Gender
    0.07
    公式
    0.07
     Gender
    0.07
     Hr
    0.07
    什么意思
    0.07
     Children's
    0.07
    Activations Density 0.066%

    No Known Activations