© 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. 25942
    Prev
    Next
    INDEX
    Explanations

    **

    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
     ted
    -0.07
     mód
    -0.07
    trecht
    -0.07
    ointed
    -0.07
     verteilt
    -0.07
    bear
    -0.07
     effort
    -0.07
    Designed
    -0.07
     bearer
    -0.07
    geh
    -0.07
    POSITIVE LOGITS
     narrator
    0.09
     pesquisadores
    0.09
     reviewers
    0.09
     chercheurs
    0.09
     девушки
    0.09
    医生
    0.09
     fabricants
    0.09
     padres
    0.09
     Sharma
    0.09
     researchers
    0.09
    Activations Density 0.018%

    No Known Activations