© 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. 91285
    Prev
    Next
    INDEX
    Explanations

    eye

    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
     Pb
    -0.08
     Ns
    -0.07
    边
    -0.07
    Pb
    -0.07
    rear
    -0.07
     Jews
    -0.07
    ble
    -0.07
     erhö
    -0.07
    .backward
    -0.07
    gebiet
    -0.07
    POSITIVE LOGITS
     видно
    0.08
    激情
    0.08
     Swap
    0.08
     heartfelt
    0.08
    交流
    0.07
     persoonlijk
    0.07
     verde
    0.07
    を見る
    0.07
    一起
    0.07
    悉
    0.07
    Activations Density 0.009%

    No Known Activations