© 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. 528
    Prev
    Next
    INDEX
    Explanations

    joint

    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
     Howard
    -0.08
    Items
    -0.08
    112
    -0.08
     Kam
    -0.08
     коллектив
    -0.08
    тын
    -0.08
    Anonymous
    -0.07
     تو
    -0.07
    Howard
    -0.07
    Moh
    -0.07
    POSITIVE LOGITS
     сустав
    0.09
     Asp
    0.08
     inflammation
    0.08
     Uns
    0.08
    炎
    0.08
     Bursa
    0.08
    酸
    0.08
     swelling
    0.07
     nas
    0.07
     phosphory
    0.07
    Activations Density 0.007%

    No Known Activations