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. 102888
    Prev
    Next
    INDEX
    Explanations

    visual consistency

    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
     Fakten
    -0.09
    -dropdown
    -0.09
    /testify
    -0.08
    _dropdown
    -0.08
     hören
    -0.08
     zuverläss
    -0.08
    _dump
    -0.08
     Facts
    -0.08
     facts
    -0.08
     القدم
    -0.08
    POSITIVE LOGITS
     thematic
    0.15
     cohesive
    0.14
    テーマ
    0.14
     temática
    0.12
     cohes
    0.12
     thème
    0.12
    主题
    0.11
    theme
    0.11
     aesthetic
    0.11
     темат
    0.11
    Activations Density 0.015%

    No Known Activations