© 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. 20025
    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
     that
    -0.11
    ].↵↵
    -0.10
    meaning
    -0.10
     its
    -0.10
    'enfant
    -0.10
    that
    -0.09
    '.↵↵
    -0.09
    iego
    -0.09
    's
    -0.09
    ielo
    -0.09
    POSITIVE LOGITS
     **↵
    0.11
    Includes
    0.11
    Current
    0.10
    Detection
    0.10
    Recommended
    0.10
    Decrease
    0.10
    Primary
    0.10
    Include
    0.10
     +↵
    0.10
    Inactive
    0.09
    Activations Density 0.020%

    No Known Activations