© 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. 68596
    Prev
    Next
    INDEX
    Explanations

    jour

    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
    성과
    -0.08
     satisfactory
    -0.08
    赶
    -0.08
     δι
    -0.08
     results
    -0.08
     Vf
    -0.08
     singles
    -0.08
    성을
    -0.07
     conclus
    -0.07
     eventually
    -0.07
    POSITIVE LOGITS
     futuristic
    0.12
     imaginative
    0.11
     تصور
    0.10
     surreal
    0.10
     imagining
    0.10
     необы
    0.10
     Imagine
    0.10
     фанта
    0.10
    ampunk
    0.10
     कल्प
    0.09
    Activations Density 0.004%

    No Known Activations