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. 112075
    Prev
    Next
    INDEX
    Explanations

    you

    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
    osity
    -0.09
    {}↵
    -0.08
     anonymity
    -0.08
     인해
    -0.08
    ution
    -0.07
     duurzaamheid
    -0.07
    Consistency
    -0.07
     ತು
    -0.07
     평가
    -0.07
    forces
    -0.07
    POSITIVE LOGITS
     ഇട
    0.08
     Delphi
    0.08
     benötigt
    0.08
     braucht
    0.08
    .float
    0.07
    .reshape
    0.07
     gweld
    0.07
     teal
    0.07
    دخل
    0.07
     fleeting
    0.07
    Activations Density 0.018%

    No Known Activations