© 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. 103179
    Prev
    Next
    INDEX
    Explanations

    sleep apnea

    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
     wounded
    -0.08
    озар
    -0.08
     Creative
    -0.08
     Pixar
    -0.08
     fleurs
    -0.07
     Bootstrap
    -0.07
    新品
    -0.07
     Thomas
    -0.07
     doctrina
    -0.07
     berries
    -0.07
    POSITIVE LOGITS
     apnea
    0.24
     slaap
    0.15
    睡
    0.15
     sleep
    0.14
     obstruct
    0.14
     النوم
    0.13
    �
    0.13
    Sleep
    0.13
     airway
    0.13
     respiratory
    0.13
    Activations Density 0.005%

    No Known Activations