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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 63027
    Prev
    Next
    INDEX
    Explanations

    Chinese concepts

    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
    退休
    -0.09
    럴
    -0.08
    Deadline
    -0.08
     scorso
    -0.08
    Expected
    -0.08
     pricey
    -0.08
    😂
    -0.08
     giveaways
    -0.08
     prett
    -0.08
     roundup
    -0.07
    POSITIVE LOGITS
     sacred
    0.10
     पृथ
    0.09
    @Table
    0.09
     يمثل
    0.09
    iversal
    0.09
     représentent
    0.09
     tượng
    0.08
    象
    0.08
     representan
    0.08
     Buddha
    0.08
    Activations Density 0.016%

    No Known Activations