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. 131067
    Prev
    Next
    INDEX
    Explanations

    find

    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
     entw
    -0.10
     Conexion
    -0.08
     Strap
    -0.08
     Poet
    -0.08
     Théâtre
    -0.07
     intertw
    -0.07
     Som
    -0.07
     bells
    -0.07
     conexion
    -0.07
     ober
    -0.07
    POSITIVE LOGITS
     kiếm
    0.10
     தே
    0.09
     ಹುಡು
    0.09
    -efficient
    0.09
    Providers
    0.09
    provider
    0.08
     specialist
    0.08
     referrals
    0.08
     jobb
    0.08
     недвижимости
    0.08
    Activations Density 0.063%

    No Known Activations