© 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. 69944
    Prev
    Next
    INDEX
    Explanations

    fortunate or lucky

    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
     Crushing
    -0.08
     PEN
    -0.08
    -driving
    -0.08
     penalties
    -0.07
     Tennis
    -0.07
     Sut
    -0.07
     Tron
    -0.07
     Truck
    -0.07
    pron
    -0.07
     Emerald
    -0.07
    POSITIVE LOGITS
     moments
    0.10
     Moments
    0.09
     privilege
    0.09
     privilegi
    0.09
     fortunate
    0.09
     reçu
    0.08
     privil
    0.08
     receipt
    0.08
     Few
    0.08
     معامل
    0.08
    Activations Density 0.028%

    No Known Activations