© 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. 102227
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
     පහ
    -0.09
     síðan
    -0.08
     साथै
    -0.08
    asilẹ
    -0.08
     löyty
    -0.08
    asil
    -0.08
     الموافق
    -0.08
     ～
    -0.08
     😀↵↵
    -0.08
    ‌,
    -0.08
    POSITIVE LOGITS
     warns
    0.12
    _warning
    0.12
     disclaimer
    0.12
    .warning
    0.12
    无法
    0.12
     slecht
    0.12
    _ERROR
    0.12
    invalid
    0.11
     incomplete
    0.11
     предупреж
    0.11
    Activations Density 0.009%

    No Known Activations