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. 411
    Prev
    Next
    INDEX
    Explanations

    recognition

    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
     increíbles
    -0.08
     الأسر
    -0.08
    Infor
    -0.08
     provinc
    -0.08
    _Value
    -0.08
     dolgo
    -0.07
    /problems
    -0.07
     nitric
    -0.07
     recientes
    -0.07
     aceasta
    -0.07
    POSITIVE LOGITS
     herken
    0.13
    辨
    0.13
     recognizable
    0.13
    识
    0.12
    識
    0.11
     branding
    0.11
     recognition
    0.10
     recogn
    0.10
     evokes
    0.10
     узна
    0.10
    Activations Density 0.016%

    No Known Activations