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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 108661
    Prev
    Next
    INDEX
    Explanations

    Get

    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
     Ul
    -0.08
     beschlossen
    -0.08
    ámica
    -0.08
     çift
    -0.08
     стане
    -0.07
     FAIR
    -0.07
    Charlotte
    -0.07
    激情
    -0.07
     twin
    -0.07
    emia
    -0.07
    POSITIVE LOGITS
     nanti
    0.08
     താഴ
    0.08
     insinu
    0.08
    0.07
     informes
    0.07
     ........
    0.07
     [...]
    0.07
     obat
    0.07
    _k
    0.07
     കൂട
    0.07
    Activations Density 0.000%
    No Known Activations