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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 120193
    Prev
    Next
    INDEX
    Explanations

    mythology

    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
    .yang
    -0.08
    机场
    -0.08
    Mach
    -0.08
     déc
    -0.08
    .sdk
    -0.08
    .operation
    -0.08
    .stdin
    -0.07
    人民币
    -0.07
     molds
    -0.07
     Maranhão
    -0.07
    POSITIVE LOGITS
     отпуск
    0.09
     ആഘ
    0.08
     празднич
    0.08
     Trag
    0.08
     Szen
    0.08
     траг
    0.08
    leden
    0.08
     трав
    0.08
     forgiveness
    0.08
     Saison
    0.08
    Activations Density 0.003%

    No Known Activations