Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120252
    Prev
    Next
    INDEX
    Explanations

    sin

    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
     Cheapest
    -0.08
    				       
    -0.07
     Neb
    -0.07
     פעילות
    -0.07
     =================================
    -0.07
     organisiert
    -0.07
     toothpaste
    -0.07
     عملی
    -0.07
     استمرار
    -0.07
    _multiple
    -0.07
    POSITIVE LOGITS
    吕
    0.08
     Rela
    0.08
     psychopath
    0.08
     ruolo
    0.07
     bout
    0.07
    クト
    0.07
    ावे
    0.07
    (pk
    0.07
     Binnen
    0.07
    和
    0.07
    Activations Density 0.006%

    No Known Activations