© 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. 11-RESID-POST-AA
    11. 108616
    Prev
    Next
    INDEX
    Explanations

    4

    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
    _progress
    -0.08
     progress
    -0.08
     smooth
    -0.07
    xmin
    -0.07
     clay
    -0.07
     belles
    -0.07
    Progress
    -0.07
    xaf
    -0.07
     للأس
    -0.07
    oons
    -0.07
    POSITIVE LOGITS
     aturan
    0.09
    enna
    0.08
     ruled
    0.08
    (rule
    0.08
    မြ
    0.08
     Rule
    0.08
     geek
    0.08
    Rule
    0.08
     reglas
    0.08
     regras
    0.08
    Activations Density 0.001%

    No Known Activations