© 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. 557
    Prev
    Next
    INDEX
    Explanations

    adem

    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
     afirm
    -0.09
     potência
    -0.09
     разработки
    -0.08
     ставки
    -0.08
     Allí
    -0.08
     endlich
    -0.08
     установки
    -0.08
     изображения
    -0.08
     познаком
    -0.08
     энергии
    -0.08
    POSITIVE LOGITS
    used
    0.09
    Nan
    0.08
     nan
    0.08
    以前
    0.08
     market
    0.07
    FE
    0.07
    科技
    0.07
    webkit
    0.07
    market
    0.07
    8
    0.07
    Activations Density 1.026%

    No Known Activations