© 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. 22113
    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
    ltf
    -0.09
    collapse
    -0.07
     flotation
    -0.07
     SSD
    -0.07
    ädt
    -0.07
     manipulation
    -0.07
     closer
    -0.07
     NBA
    -0.07
     DOM
    -0.07
     STL
    -0.07
    POSITIVE LOGITS
     peppers
    0.24
    辣
    0.23
     pepper
    0.22
    椒
    0.21
     chili
    0.20
     Pepper
    0.19
     spices
    0.19
     chilli
    0.18
     paprika
    0.18
     spicy
    0.17
    Activations Density 0.026%

    No Known Activations