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. 44004
    Prev
    Next
    INDEX
    Explanations

    WASD controls

    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
     allerg
    -0.08
    ALE
    -0.08
    ijzen
    -0.08
    alit
    -0.07
    /testify
    -0.07
     celebrity
    -0.07
     Allergy
    -0.07
     elektr
    -0.07
    _www
    -0.07
    ikhail
    -0.07
    POSITIVE LOGITS
    ่าน
    0.08
     roughly
    0.08
     movement
    0.08
     движения
    0.07
    ospatial
    0.07
    movement
    0.07
    Spatial
    0.07
     affin
    0.07
     enabled
    0.07
     presenza
    0.07
    Activations Density 0.001%

    No Known Activations