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. 106143
    Prev
    Next
    INDEX
    Explanations

    Reduce consumption and decluttering

    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
    шты
    -0.09
     Microsoft
    -0.08
     prote
    -0.08
    アップ
    -0.08
    Microsoft
    -0.08
     shug
    -0.07
    akosha
    -0.07
    кты
    -0.07
     wichtige
    -0.07
     regulatory
    -0.07
    POSITIVE LOGITS
     appreciate
    0.09
     பயன்ப
    0.08
     camion
    0.08
     immédiatement
    0.08
     일이
    0.07
     Immediately
    0.07
     Feast
    0.07
     repayment
    0.07
    elja
    0.07
     Sauna
    0.07
    Activations Density 0.024%

    No Known Activations