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. 77170
    Prev
    Next
    INDEX
    Explanations

    Settings and editing

    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
    iyo
    -0.09
    居民
    -0.08
    Traveler
    -0.08
    avelength
    -0.08
    503
    -0.08
    riften
    -0.08
    体系
    -0.08
     மேற்க
    -0.08
     lecz
    -0.08
     Newark
    -0.08
    POSITIVE LOGITS
     icon
    0.11
    -shaped
    0.09
    �
    0.09
    _icon
    0.09
     Icon
    0.09
    Icon
    0.09
     icons
    0.09
    -icon
    0.09
    ️
    0.09
    �
    0.09
    Activations Density 0.012%

    No Known Activations