Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55885
    Prev
    Next
    INDEX
    Explanations

    1984

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uplicate
    -0.09
    ometry
    -0.08
    Calibration
    -0.08
    (pol
    -0.08
     polym
    -0.08
     kasih
    -0.07
     duplicated
    -0.07
    (callback
    -0.07
     هنر
    -0.07
    _CAM
    -0.07
    POSITIVE LOGITS
     discusses
    0.08
     narrator
    0.08
    compagn
    0.08
     പറയുന്നു
    0.08
    ്ല
    0.08
     પગ
    0.07
     apresentados
    0.07
     bisher
    0.07
    bah
    0.07
    Bow
    0.07
    Activations Density 0.006%

    No Known Activations