© 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. 95248
    Prev
    Next
    INDEX
    Explanations

    me

    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
     elite
    -0.08
     Conscious
    -0.08
    олев
    -0.08
     ABO
    -0.07
     الساخ
    -0.07
     البول
    -0.07
    ด
    -0.07
     Rapport
    -0.07
    -0.07
    uchte
    -0.07
    POSITIVE LOGITS
    forget
    0.09
    (nullptr
    0.08
     forget
    0.08
     necklaces
    0.08
    -pin
    0.08
     forgetting
    0.08
    견
    0.08
    (marker
    0.08
    (keyword
    0.08
    {}",
    0.08
    Activations Density 0.003%
    No Known Activations