© 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. 20159
    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
    /index
    -0.10
    /views
    -0.10
    /resources
    -0.10
    /software
    -0.10
    /reference
    -0.09
    /code
    -0.09
    /Text
    -0.09
     teine
    -0.09
    /process
    -0.09
    /program
    -0.09
    POSITIVE LOGITS
     union
    0.12
     Union
    0.09
    cup
    0.09
     UNION
    0.09
    .union
    0.09
    Union
    0.09
    union
    0.09
    )|(
    0.08
     combined
    0.08
     unions
    0.08
    Activations Density 0.010%

    No Known Activations