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. 11-RESID-POST-AA
    6. 30582
    Prev
    Next
    INDEX
    Explanations

    per each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ఘ
    -0.08
     kehid
    -0.08
     insomnia
    -0.08
     Seriously
    -0.08
     Naw
    -0.07
    aaa
    -0.07
     जिंदगी
    -0.07
     Eisen
    -0.07
     overlijden
    -0.07
    Dub
    -0.07
    POSITIVE LOGITS
     elever
    0.12
     everyone's
    0.11
     എല്ലാവ
    0.11
     વિદ્યાર્થીઓ
    0.11
     विद्यार्थ
    0.10
     വിതരണം
    0.10
     everyone
    0.10
     alunos
    0.10
     shortages
    0.10
    everyone
    0.10
    Activations Density 0.047%

    No Known Activations