© 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. 95080
    Prev
    Next
    INDEX
    Explanations

    vertical/diagonal lines

    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
     аш
    -0.08
     откры
    -0.08
    ель
    -0.08
     роб
    -0.08
    चक
    -0.07
     ліку
    -0.07
    ర్చ
    -0.07
     neem
    -0.07
    mute
    -0.07
     mình
    -0.07
    POSITIVE LOGITS
     Heide
    0.08
     pret
    0.08
     ayrı
    0.08
     halinde
    0.08
     afkomstig
    0.08
     ([]
    0.08
    115
    0.08
     Philosophy
    0.07
    Nou
    0.07
    /thread
    0.07
    Activations Density 0.003%

    No Known Activations