Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54268
    Prev
    Next
    INDEX
    Explanations

    chart

    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
     JUL
    -0.08
     ETH
    -0.07
     rind
    -0.07
     verte
    -0.07
     cult
    -0.07
     Breed
    -0.07
     ממ
    -0.07
    ona
    -0.07
     Verte
    -0.07
     act
    -0.07
    POSITIVE LOGITS
    规则
    0.10
    仕様
    0.09
    通常
    0.09
    区别
    0.09
    一般
    0.09
    常
    0.08
    规定
    0.08
     Convention
    0.08
    语言
    0.08
     assumes
    0.08
    Activations Density 0.008%

    No Known Activations