© 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. 23-RESID-POST-AA
    11. 48798
    Prev
    Next
    INDEX
    Explanations

    say the ending -ist

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ففي
    -0.08
     انقلاب
    -0.08
     verschenen
    -0.07
    中大奖
    -0.07
     caída
    -0.07
     جاءت
    -0.07
     کرتا
    -0.07
     جبکہ
    -0.07
     арасында
    -0.07
     کھیل
    -0.07
    POSITIVE LOGITS
     persists
    0.38
     lasts
    0.33
     persisted
    0.33
     persist
    0.32
     lasted
    0.31
     durar
    0.30
     endured
    0.29
     endure
    0.29
     durer
    0.29
    persist
    0.29
    Activations Density 0.061%

    No Known Activations