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. 88337
    Prev
    Next
    INDEX
    Explanations

    of

    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
     weaker
    -0.08
     primitive
    -0.08
    xiom
    -0.08
     interfering
    -0.07
    primitive
    -0.07
    Primitive
    -0.07
    igator
    -0.07
     Primitive
    -0.07
    ………
    -0.07
    |||
    -0.07
    POSITIVE LOGITS
     દિવસે
    0.10
     순간
    0.09
     ദിവസം
    0.09
    鞋
    0.09
     الموافق
    0.09
     రోజు
    0.08
    当天
    0.08
     lancer
    0.08
     araw
    0.08
     அன்று
    0.08
    Activations Density 0.046%

    No Known Activations