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. 7-RESID-POST-AA
    6. 131041
    Prev
    Next
    INDEX
    Explanations

    Greek/Hellenic civilization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wing
    -0.08
    (mask
    -0.08
    erana
    -0.08
     Ber
    -0.08
    (length
    -0.08
    forme
    -0.08
    Ber
    -0.08
    holder
    -0.07
    ieran
    -0.07
    (min
    -0.07
    POSITIVE LOGITS
     олим
    0.10
     elek
    0.09
     Pall
    0.09
     Orthodox
    0.08
     konkur
    0.08
     Statue
    0.08
     damals
    0.08
     അയ
    0.08
     Przy
    0.08
    .Plugin
    0.08
    Activations Density 0.006%

    No Known Activations