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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103016
    Prev
    Next
    INDEX
    Explanations

    work

    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
     humilde
    -0.09
     melod
    -0.09
     begro
    -0.08
     нанос
    -0.08
     xml
    -0.08
    .bump
    -0.08
     हमला
    -0.08
     آسیب
    -0.08
     ennem
    -0.08
     sprites
    -0.08
    POSITIVE LOGITS
     fleks
    0.14
     flexibil
    0.14
    勤務
    0.14
     flexibility
    0.14
     hybride
    0.14
    办公
    0.13
     accommodations
    0.13
    (employee
    0.13
     arrangements
    0.13
     flexible
    0.13
    Activations Density 0.034%

    No Known Activations