© 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. 94880
    Prev
    Next
    INDEX
    Explanations

    i

    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
     перед
    -0.07
     compel
    -0.07
     предмет
    -0.07
     schaffen
    -0.07
     create
    -0.07
     Pū
    -0.07
     prema
    -0.06
     Moral
    -0.06
     можуть
    -0.06
     clash
    -0.06
    POSITIVE LOGITS
    诈骗
    0.09
    骗局
    0.09
    骗子
    0.08
    illère
    0.08
     dehydr
    0.08
    otrop
    0.08
    -dropdown
    0.08
    AWA
    0.08
     sonrası
    0.07
    姑娘
    0.07
    Activations Density 0.001%

    No Known Activations