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. 13039
    Prev
    Next
    INDEX
    Explanations

    social

    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
     asas
    -0.08
     wit
    -0.08
    ilateral
    -0.08
    itimate
    -0.08
    imized
    -0.08
     ICA
    -0.07
    itis
    -0.07
     tril
    -0.07
     dax
    -0.07
     vain
    -0.07
    POSITIVE LOGITS
     társ
    0.11
    /social
    0.10
     societal
    0.10
    社会
    0.10
     society
    0.09
     sociais
    0.09
     społ
    0.09
     sociaux
    0.09
     ಸಮಾಜ
    0.09
     समाज
    0.09
    Activations Density 0.040%

    No Known Activations