© 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. 44536
    Prev
    Next
    INDEX
    Explanations

    Image compression/optimization

    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
     quid
    -0.09
    ್ತು
    -0.09
     документ
    -0.09
     dokument
    -0.08
     tood
    -0.08
     gudanar
    -0.08
     документы
    -0.08
     डॉक
    -0.08
    documents
    -0.08
     학교
    -0.08
    POSITIVE LOGITS
     Compression
    0.12
    Optimizer
    0.11
     compressors
    0.11
     optimization
    0.11
     Compress
    0.11
     Optimization
    0.11
    .optimize
    0.11
    优化
    0.11
     compression
    0.10
    Compress
    0.10
    Activations Density 0.003%

    No Known Activations