© 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. 7-RESID-POST-AA
    11. 1425
    Prev
    Next
    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     umbre
    -0.08
    Lav
    -0.07
     lav
    -0.07
     Jamie
    -0.07
    企
    -0.07
     firearm
    -0.07
     Lav
    -0.07
    dog
    -0.07
    adara
    -0.07
     Qin
    -0.07
    POSITIVE LOGITS
    🏼
    0.09
    🏻
    0.08
     constit
    0.08
     Kah
    0.08
    ibration
    0.08
    ibles
    0.07
     quartiers
    0.07
     nik
    0.07
     Teen
    0.07
     Constit
    0.07
    Activations Density 0.022%

    No Known Activations