© 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. 26383
    Prev
    Next
    INDEX
    Explanations

    seek

    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
    배
    -0.08
     wyd
    -0.07
     DOM
    -0.07
     उत्प
    -0.07
    Donnell
    -0.07
    貌
    -0.07
    wife
    -0.07
     ammon
    -0.07
     राज
    -0.07
     unters
    -0.07
    POSITIVE LOGITS
    咨询
    0.12
     consulter
    0.11
     bantuan
    0.10
     neurolog
    0.10
     مراجعه
    0.10
     обратиться
    0.10
     odborn
    0.10
     hulp
    0.10
    寻
    0.10
     deskund
    0.10
    Activations Density 0.036%

    No Known Activations