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. 58717
    Prev
    Next
    INDEX
    Explanations

    React code

    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
    .xlsx
    -0.08
     sera
    -0.07
     textiles
    -0.07
     inflation
    -0.07
     curricula
    -0.07
     stud
    -0.07
    §
    -0.07
    .styles
    -0.07
     elites
    -0.07
     Greenwich
    -0.07
    POSITIVE LOGITS
    _wrap
    0.09
     Wrap
    0.09
     Wrapper
    0.08
    rous
    0.08
     vorbei
    0.08
    mtree
    0.08
    joch
    0.08
    Wrapper
    0.08
    _wrapper
    0.08
    Wrap
    0.08
    Activations Density 0.005%

    No Known Activations