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. 15-RESID-POST-AA
    6. 19316
    Prev
    Next
    INDEX
    Explanations

    overlap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _today
    -0.08
     Cycling
    -0.08
    _name
    -0.07
     Mascul
    -0.07
     cumin
    -0.07
    iesel
    -0.07
     greet
    -0.07
     Fridays
    -0.07
    umulator
    -0.07
     ganska
    -0.07
    POSITIVE LOGITS
    Overlap
    0.14
     overlapping
    0.13
     illegally
    0.13
     overlap
    0.13
     overlaps
    0.12
     protr
    0.12
    _overlap
    0.12
     undue
    0.12
     excessive
    0.11
     unauthorized
    0.10
    Activations Density 0.009%

    No Known Activations