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. 30010
    Prev
    Next
    INDEX
    Explanations

    rice

    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
    诈
    -0.09
     Private
    -0.08
    šem
    -0.08
     catastrophic
    -0.08
     private
    -0.08
     fileprivate
    -0.08
    针
    -0.08
    ,:),
    -0.08
    жет
    -0.08
     severe
    -0.08
    POSITIVE LOGITS
     libros
    0.08
     කරන්න
    0.08
    /blog
    0.07
    Tutorial
    0.07
    Podcast
    0.07
     Jungle
    0.07
    搭
    0.07
    米
    0.07
     Peters
    0.07
     Vortrag
    0.07
    Activations Density 0.004%

    No Known Activations