© 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. 26502
    Prev
    Next
    INDEX
    Explanations

    since

    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
     puedo
    -0.09
     Southeastern
    -0.09
     Пов
    -0.07
     convi
    -0.07
     Bahr
    -0.07
    -background
    -0.07
     desf
    -0.07
     tz
    -0.07
     researches
    -0.07
    )t
    -0.07
    POSITIVE LOGITS
     sonst
    0.11
     otherwise
    0.10
     જેથી
    0.09
     presumably
    0.09
    这是
    0.09
    Otherwise
    0.08
    否则
    0.08
     afinal
    0.08
     иначе
    0.08
     Musa
    0.08
    Activations Density 0.054%

    No Known Activations