© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12885
    Prev
    Next
    INDEX
    Explanations

    шаг

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fusion
    -0.08
     Huawei
    -0.08
     ford
    -0.08
     offici
    -0.08
     Fais
    -0.08
     kah
    -0.08
     AFC
    -0.07
     fused
    -0.07
     حر
    -0.07
     сообщения
    -0.07
    POSITIVE LOGITS
     Mor
    0.08
    Mor
    0.07
     న
    0.07
    ನೇ
    0.07
    惯
    0.07
    不得
    0.07
    vc
    0.07
     mają
    0.07
    Cas
    0.07
    寒
    0.07
    Activations Density 0.000%

    No Known Activations