© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 833
    Prev
    Next
    INDEX
    Explanations

    ar

    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
    (activity
    -0.08
     spac
    -0.08
     miesz
    -0.08
     ост
    -0.08
     सुध
    -0.07
    Λ
    -0.07
     activités
    -0.07
     nic
    -0.07
    .optim
    -0.07
     growth
    -0.07
    POSITIVE LOGITS
     whatsoever
    0.09
     george
    0.08
     gewisse
    0.08
     geist
    0.08
    ~↵↵
    0.08
     clase
    0.08
     piedra
    0.07
    石
    0.07
     kull
    0.07
     executes
    0.07
    Activations Density 0.003%

    No Known Activations