© 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. 20464
    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
     batches
    -0.09
    ==
    -0.08
    不到账
    -0.08
     долларов
    -0.08
     त्य
    -0.08
     bearish
    -0.08
     those
    -0.08
    addii
    -0.08
    ===
    -0.08
    issaq
    -0.08
    POSITIVE LOGITS
     réglementation
    0.09
     accompagné
    0.09
     representação
    0.08
     représentation
    0.08
     تشکیل
    0.08
     expressing
    0.07
     aimed
    0.07
     budu
    0.07
     representación
    0.07
    Representation
    0.07
    Activations Density 0.000%

    No Known Activations