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. 60902
    Prev
    Next
    INDEX
    Explanations

    century

    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
     frontières
    -0.08
     sév
    -0.08
     Pied
    -0.08
    .bound
    -0.08
     देते
    -0.07
     quae
    -0.07
     Cotton
    -0.07
    bound
    -0.07
    ơi
    -0.07
     Continental
    -0.07
    POSITIVE LOGITS
    ipro
    0.08
    ىل
    0.08
     worthwhile
    0.08
     oprav
    0.08
    春
    0.07
    没
    0.07
    andering
    0.07
    -imi
    0.07
    Wis
    0.07
     unjust
    0.07
    Activations Density 0.023%

    No Known Activations