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. 77248
    Prev
    Next
    INDEX
    Explanations

    Beef

    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
     descont
    -0.09
     Gibbs
    -0.08
    一本
    -0.08
     cumpleaños
    -0.08
    τισ
    -0.08
     domingos
    -0.08
    返点
    -0.08
    lighet
    -0.08
    щик
    -0.07
     correo
    -0.07
    POSITIVE LOGITS
     BOOLEAN
    0.07
     lymph
    0.07
     Collaboration
    0.07
    েয়
    0.07
    YOUR
    0.07
    Business
    0.07
    ায
    0.07
     �
    0.07
    ाय
    0.07
     Sioux
    0.07
    Activations Density 0.013%

    No Known Activations