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. 52921
    Prev
    Next
    INDEX
    Explanations

    wizard, auto

    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
     cooled
    -0.08
     remind
    -0.08
    Cooldown
    -0.08
    _fc
    -0.08
     chilling
    -0.07
     cooldown
    -0.07
     meditate
    -0.07
    _(
    -0.07
     пох
    -0.07
     seper
    -0.07
    POSITIVE LOGITS
     automáticamente
    0.08
     automatiquement
    0.08
     automatisch
    0.08
    ેલ
    0.08
     automaticamente
    0.08
     connectivity
    0.08
     aangeboden
    0.07
    自动
    0.07
    寻找
    0.07
     geprobeerd
    0.07
    Activations Density 0.007%

    No Known Activations