© 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. 31022
    Prev
    Next
    INDEX
    Explanations

    ||

    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
     cuc
    -0.08
    俱
    -0.07
    히
    -0.07
    領
    -0.07
     Mons
    -0.07
     duk
    -0.07
     pagp
    -0.07
     adecuado
    -0.07
     fosters
    -0.07
    ಿಂತ
    -0.07
    POSITIVE LOGITS
    cont
    0.07
     adolescent
    0.07
     Pry
    0.07
     Reid
    0.07
     paut
    0.07
     sand
    0.07
     Gulf
    0.07
     Manuel
    0.07
    hali
    0.07
     Painter
    0.07
    Activations Density 0.025%

    No Known Activations