© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 103518
    Prev
    Next
    INDEX
    Explanations

    ery

    np_max-act-logits · gemini-2.0-flash
    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
     FHA
    -0.10
     ~(
    -0.08
     MINI
    -0.08
     spared
    -0.08
     Malaysian
    -0.08
    北海道
    -0.08
     fha
    -0.08
     MGA
    -0.08
    .snp
    -0.08
     nautical
    -0.08
    POSITIVE LOGITS
     workers
    0.27
     worker
    0.26
    .worker
    0.23
     Workers
    0.23
    _worker
    0.22
    Worker
    0.22
    worker
    0.22
    Workers
    0.22
     celery
    0.21
     Worker
    0.21
    Activations Density 0.006%

    No Known Activations