© 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. 45295
    Prev
    Next
    INDEX
    Explanations

    incentive

    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
     Conv
    -0.08
    ্যার
    -0.08
    Conv
    -0.07
     Nub
    -0.07
     Mercer
    -0.07
    拾
    -0.07
     Mets
    -0.07
     Avi
    -0.07
     infin
    -0.07
     bijdrage
    -0.07
    POSITIVE LOGITS
    措施
    0.11
    事項
    0.08
    事项
    0.08
    Bol
    0.07
     ц
    0.07
    prin
    0.07
    ILO
    0.07
     현
    0.07
     만
    0.07
     accru
    0.07
    Activations Density 0.004%

    No Known Activations