© 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 EvalsExportsAPI 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. 19877
    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
     customization
    -0.08
     בדיוק
    -0.08
    Customization
    -0.08
    'intégr
    -0.08
     हिं
    -0.08
     дорож
    -0.07
    撞
    -0.07
    TEGR
    -0.07
     Trauma
    -0.07
     безопасности
    -0.07
    POSITIVE LOGITS
     indoor
    0.14
     shaded
    0.14
     indoors
    0.14
     shade
    0.14
    Indoor
    0.13
     shady
    0.13
    Shade
    0.13
     sunscreen
    0.13
     вент
    0.12
     Indoor
    0.12
    Activations Density 0.018%

    No Known Activations