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. 169
    Prev
    Next
    INDEX
    Explanations

    math terms

    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
    _palette
    -0.08
    palette
    -0.08
    /on
    -0.08
     또는
    -0.08
     부족
    -0.08
    converted
    -0.07
    .convert
    -0.07
     ואף
    -0.07
     Local
    -0.07
    POSITIVE LOGITS
    ាមួយ
    0.09
    әшә
    0.08
    ánt
    0.08
    We're
    0.08
     only
    0.08
    』
    0.08
    096
    0.08
     focuses
    0.08
     gyfer
    0.08
    ”:
    0.07
    Activations Density 0.131%

    No Known Activations