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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 77263
    Prev
    Next
    INDEX
    Explanations

    academic/business writing

    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
     Tsy
    -0.08
    .delay
    -0.08
     إجراء
    -0.08
    ceries
    -0.08
     Multi
    -0.07
     задания
    -0.07
     সো
    -0.07
     objet
    -0.07
     atras
    -0.07
     CFDs
    -0.07
    POSITIVE LOGITS
     ecosystem
    0.12
     realm
    0.12
     arsenal
    0.11
    体系
    0.11
     repertoire
    0.11
     landscape
    0.11
     spectrum
    0.10
     workforce
    0.10
     regime
    0.10
     oeuvre
    0.10
    Activations Density 0.152%

    No Known Activations