© 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. 31026
    Prev
    Next
    INDEX
    Explanations

    referee/officiate

    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
     Gru
    -0.08
     Managua
    -0.08
    નાર
    -0.07
    িমান
    -0.07
     Hond
    -0.07
     Ма
    -0.07
    ogi
    -0.07
     Hugo
    -0.07
     Augustine
    -0.07
     Higgins
    -0.07
    POSITIVE LOGITS
     مباريات
    0.08
     맡
    0.08
     variety
    0.08
     noites
    0.07
    710
    0.07
     basketball
    0.07
     Fires
    0.07
     maternity
    0.07
     عروض
    0.07
     babys
    0.07
    Activations Density 0.008%

    No Known Activations