© 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. 103009
    Prev
    Next
    INDEX
    Explanations

    matrix dimensions

    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
     swarm
    -0.09
     ہونا
    -0.09
     perimeter
    -0.08
     gefe
    -0.08
     celebración
    -0.08
     proseso
    -0.08
     tile
    -0.08
     paisaje
    -0.08
     feiern
    -0.08
     процесса
    -0.08
    POSITIVE LOGITS
    -dimensional
    0.17
    ×
    0.14
    x
    0.12
     ×
    0.11
    -by
    0.11
    -component
    0.11
     dimensional
    0.11
    -element
    0.11
    -row
    0.10
    -tu
    0.10
    Activations Density 0.009%

    No Known Activations