© 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. 79133
    Prev
    Next
    INDEX
    Explanations

    backup

    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
    淘
    -0.09
     aktar
    -0.08
     newfound
    -0.08
     الجزء
    -0.07
     gull
    -0.07
     manque
    -0.07
     pearl
    -0.07
     iceberg
    -0.07
     radar
    -0.07
    erli
    -0.07
    POSITIVE LOGITS
     必胜
    0.08
     നിങ്ങ
    0.08
     estratégia
    0.08
    ивали
    0.08
     Wednesdays
    0.07
     ҳам
    0.07
     भूमि
    0.07
     backups
    0.07
     baked
    0.07
     उपाय
    0.07
    Activations Density 0.002%

    No Known Activations