© 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. 30237
    Prev
    Next
    INDEX
    Explanations

    at

    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
     byť
    -0.07
    Infl
    -0.07
    'import
    -0.07
    <Tree
    -0.07
     বৃ
    -0.07
    ające
    -0.07
     Onion
    -0.07
     infl
    -0.07
     interconnected
    -0.07
    acie
    -0.07
    POSITIVE LOGITS
     HOME
    0.09
     Missouri
    0.09
     홈
    0.09
    HOME
    0.08
     Utrecht
    0.08
     home
    0.08
     Indianapolis
    0.08
     mexico
    0.08
     Arizona
    0.08
     Wisconsin
    0.08
    Activations Density 0.014%

    No Known Activations