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. 77329
    Prev
    Next
    INDEX
    Explanations

    are

    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
     illet
    -0.08
     eut
    -0.08
    verbrauch
    -0.08
    аем
    -0.08
    ajen
    -0.08
     preciosa
    -0.07
    atinum
    -0.07
     sade
    -0.07
     Aj
    -0.07
    /native
    -0.07
    POSITIVE LOGITS
     contexto
    0.11
     contexte
    0.10
     context
    0.10
    context
    0.10
     сюжет
    0.09
     Context
    0.09
     Kontext
    0.09
     surrounding
    0.09
     beforehand
    0.09
    剧情
    0.09
    Activations Density 0.017%

    No Known Activations