Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 19203
    Prev
    Next
    INDEX
    Explanations

    Foreign conjunctions

    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
    ‍්
    -0.08
    בן
    -0.08
    dup
    -0.08
     gladi
    -0.08
    endous
    -0.08
     colony
    -0.07
    .bg
    -0.07
    රු
    -0.07
    [](
    -0.07
    igl
    -0.07
    POSITIVE LOGITS
     hence
    0.09
     donc
    0.09
     but
    0.08
     ஆனால்
    0.08
     이하
    0.07
     nhưng
    0.07
     incum
    0.07
     portanto
    0.07
     aber
    0.07
     dunque
    0.07
    Activations Density 0.024%

    No Known Activations