© 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. 65462
    Prev
    Next
    INDEX
    Explanations

    Foreign language text

    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
     broadly
    -0.08
     chaleureux
    -0.08
     guilt
    -0.08
     jurídico
    -0.07
    lesh
    -0.07
    Boston
    -0.07
    noch
    -0.07
    .Managed
    -0.07
    升级
    -0.07
     Detroit
    -0.07
    POSITIVE LOGITS
     stature
    0.13
     tallest
    0.10
    -standing
    0.10
     taller
    0.09
    พร
    0.09
    สูง
    0.09
     erect
    0.09
    -reaching
    0.09
     جدًا
    0.09
     pinnacle
    0.09
    Activations Density 0.032%

    No Known Activations