© 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. 19513
    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
     Scripts
    -0.12
    @Service
    -0.11
     Stimme
    -0.10
    _scripts
    -0.10
    Unix
    -0.10
     scripts
    -0.10
     Unix
    -0.10
    /scripts
    -0.10
    .files
    -0.10
    .script
    -0.10
    POSITIVE LOGITS
     polygon
    0.19
     quadr
    0.19
     четырех
    0.18
     quart
    0.16
     четыр
    0.16
    Quadr
    0.16
    _polygon
    0.16
     tetra
    0.16
     rectangle
    0.15
     quadru
    0.15
    Activations Density 0.071%

    No Known Activations