© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70227
    Prev
    Next
    INDEX
    Explanations

    programming class vs struct

    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
     setzte
    -0.08
    'énergie
    -0.08
    ชั่น
    -0.08
     Presence
    -0.07
     Gradient
    -0.07
    ضور
    -0.07
     gradients
    -0.07
    Gradient
    -0.07
     Offline
    -0.07
     presença
    -0.07
    POSITIVE LOGITS
    alphabet
    0.08
     mainly
    0.08
    -items
    0.08
     Kleidung
    0.08
    default
    0.08
    clairage
    0.08
    bene
    0.08
    mostly
    0.08
    login
    0.07
     deduct
    0.07
    Activations Density 0.001%

    No Known Activations