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. 98282
    Prev
    Next
    INDEX
    Explanations

    Personal lists or collections

    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
     увеличить
    -0.08
     Incident
    -0.08
     לדבר
    -0.08
     legitimacy
    -0.07
    Incident
    -0.07
    079
    -0.07
     обращаться
    -0.07
    Obstacle
    -0.07
     להע
    -0.07
     цены
    -0.07
    POSITIVE LOGITS
     scrapbook
    0.11
    wishlist
    0.10
     personnelle
    0.10
     personalize
    0.10
    _saved
    0.09
     persönliche
    0.09
     personal
    0.09
     persoonlijke
    0.09
     personalized
    0.09
    Wishlist
    0.09
    Activations Density 0.031%

    No Known Activations