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. 113969
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
    ziehen
    -0.08
     Orn
    -0.07
     elegance
    -0.07
     landscaping
    -0.07
     London
    -0.07
    �
    -0.07
     Ward
    -0.07
    രു
    -0.07
    +
    -0.07
     relocating
    -0.07
    POSITIVE LOGITS
     حق
    0.08
     individuelles
    0.08
    ">↵↵↵
    0.08
     Boost
    0.08
     substantially
    0.07
     rigtig
    0.07
    统计
    0.07
     类型
    0.07
     individuel
    0.07
     ಮಾನ
    0.07
    Activations Density 0.016%

    No Known Activations