© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68403
    Prev
    Next
    INDEX
    Explanations

    duplicate

    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
    協
    -0.08
     generous
    -0.08
     stays
    -0.08
     cooperative
    -0.07
     medicinal
    -0.07
    работ
    -0.07
     patience
    -0.07
     stayed
    -0.07
     Makes
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     duplicate
    0.13
    Duplicate
    0.13
    duplicate
    0.12
    _duplicates
    0.12
    Duplicates
    0.12
     Duplicate
    0.12
    _duplicate
    0.11
     duplication
    0.10
     duplicates
    0.10
    重复
    0.10
    Activations Density 0.008%

    No Known Activations