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

    Neuronpedia

    Jacobian LensNEW
    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. 69633
    Prev
    Next
    INDEX
    Explanations

    words

    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
     मिलने
    -0.08
    kod
    -0.07
     Mrs
    -0.07
    deren
    -0.07
     granny
    -0.07
    ırlar
    -0.07
     ii
    -0.07
    -0.07
     temporary
    -0.07
    하거나
    -0.07
    POSITIVE LOGITS
    Excerpt
    0.08
    _Left
    0.08
     пришлось
    0.08
    love
    0.08
     председ
    0.08
     excerpts
    0.08
    estic
    0.08
     excerpt
    0.08
     bitter
    0.08
    gmt
    0.08
    Activations Density 0.012%

    No Known Activations