© 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. 99337
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
     الأط
    -0.09
     أغ
    -0.09
    FTA
    -0.08
     أط
    -0.08
     spin
    -0.08
    Spin
    -0.08
     maju
    -0.08
    engineering
    -0.08
     Spin
    -0.08
     மக்கள்
    -0.07
    POSITIVE LOGITS
    🏼
    0.10
     Technician
    0.08
    ships
    0.08
    岗位
    0.08
    🏻
    0.08
     respectfully
    0.08
     technician
    0.07
     esquer
    0.07
     Evid
    0.07
    份
    0.07
    Activations Density 0.021%

    No Known Activations