© 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. 79028
    Prev
    Next
    INDEX
    Explanations

    "how to" instructions

    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
     hypothesis
    -0.09
    Honor
    -0.08
     honra
    -0.08
     Бай
    -0.08
     assertion
    -0.08
    .Result
    -0.07
    ীক্ষ
    -0.07
     orsz
    -0.07
    Pago
    -0.07
    Assertion
    -0.07
    POSITIVE LOGITS
    教程
    0.16
    指导
    0.15
    指南
    0.15
     consejos
    0.14
     советы
    0.14
     tutorials
    0.14
     conseils
    0.14
     advice
    0.13
     Anleitung
    0.13
     안내
    0.13
    Activations Density 0.389%

    No Known Activations