© 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. 23-RESID-POST-AA
    11. 47822
    Prev
    Next
    INDEX
    Explanations

    pul

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    自在
    -0.08
     kes
    -0.08
     слишком
    -0.08
    ‘z
    -0.08
     kush
    -0.08
     الحالة
    -0.07
    iloeng
    -0.07
     deine
    -0.07
     ($_
    -0.07
     Jake
    -0.07
    POSITIVE LOGITS
    monary
    0.21
    vic
    0.10
    mon
    0.09
    MON
    0.09
    ગાર
    0.09
    m
    0.08
    icare
    0.08
    viso
    0.08
    _mon
    0.08
    _so
    0.08
    Activations Density 0.001%

    No Known Activations