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. 76077
    Prev
    Next
    INDEX
    Explanations

    virtual reality collaboration

    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
    asya
    -0.08
    isir
    -0.08
    ree
    -0.07
     cleaners
    -0.07
    reek
    -0.07
    ekw
    -0.07
    rij
    -0.07
    hw
    -0.07
     связи
    -0.07
     evidence
    -0.07
    POSITIVE LOGITS
    共享
    0.14
    多人
    0.13
    /shared
    0.12
     공유
    0.12
    共有
    0.12
     multiplayer
    0.11
     condiv
    0.11
     공동
    0.11
    .shared
    0.11
     શેર
    0.10
    Activations Density 0.045%

    No Known Activations