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. 23-RESID-POST-AA
    6. 131030
    Prev
    Next
    INDEX
    Explanations

    comma

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     విన
    -0.08
     hat
    -0.08
     hak
    -0.08
    ů
    -0.07
     uumm
    -0.07
     effe
    -0.07
     realm
    -0.07
     realms
    -0.07
     Imm
    -0.07
    алады
    -0.07
    POSITIVE LOGITS
     p
    0.09
    p
    0.08
     pediu
    0.07
     бог
    0.07
    pe
    0.07
    $$$$
    0.07
    Pe
    0.07
     Gwyn
    0.07
     Pe
    0.07
     диагности
    0.07
    Activations Density 0.001%

    No Known Activations