© 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. 19-RESID-POST-AA
    11. 102189
    Prev
    Next
    INDEX
    Explanations

    micro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <|end|>
    -0.09
     ως
    -0.08
     සඳහා
    -0.08
    (es
    -0.08
     என்பது
    -0.08
    
    -0.08
    ệnh
    -0.08
    (level
    -0.08
     அதன்
    -0.08
     отношения
    -0.08
    POSITIVE LOGITS
    ప్ప
    0.09
    ంత్ర
    0.09
    services
    0.08
     vineyards
    0.08
     businesses
    0.08
     hotels
    0.08
    Satellite
    0.08
    -library
    0.08
    ibraries
    0.08
     pero
    0.08
    Activations Density 0.006%

    No Known Activations