© 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. 29611
    Prev
    Next
    INDEX
    Explanations

    MP

    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
     amuse
    -0.08
    istry
    -0.08
     pain
    -0.07
     ಜನ
    -0.07
     Bier
    -0.07
    数量
    -0.07
     ಕ್ಷೇತ್ರ
    -0.07
    Gee
    -0.07
    -generation
    -0.07
     elector
    -0.07
    POSITIVE LOGITS
     fors
    0.09
     البيان
    0.08
     tonos
    0.08
     Tung
    0.08
     вперед
    0.08
    úva
    0.08
     وراء
    0.08
     перейти
    0.08
     freestyle
    0.08
     tới
    0.07
    Activations Density 0.001%

    No Known Activations