© 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. 19-RESID-POST-AA
    11. 21597
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’assurer
    -0.11
    ’été
    -0.10
    ’île
    -0.10
    ’assurance
    -0.09
     威尼斯人
    -0.09
    ’étranger
    -0.09
    ’una
    -0.09
     Spazier
    -0.09
    ’éviter
    -0.09
    ’expression
    -0.09
    POSITIVE LOGITS
    Also
    0.11
    Multiple
    0.10
     "
    0.10
     также
    0.10
    Commands
    0.09
    Command
    0.09
    _create
    0.09
    .commands
    0.09
    Action
    0.09
    Instructions
    0.09
    Activations Density 0.008%

    No Known Activations