© 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. 108585
    Prev
    Next
    INDEX
    Explanations

    之外

    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
     loan
    -0.08
    ಾಲ
    -0.07
     knack
    -0.07
     MDR
    -0.07
    춰
    -0.07
     quid
    -0.07
    _ele
    -0.07
    ɛm
    -0.07
    ೇಹ
    -0.07
     Ea
    -0.07
    POSITIVE LOGITS
     pastries
    0.08
     हर
    0.08
    任
    0.08
     કોઈ
    0.08
     कोई
    0.08
    なら
    0.08
     कौन
    0.08
     מכל
    0.08
     सभी
    0.08
    gawe
    0.08
    Activations Density 0.008%

    No Known Activations