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. 75988
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     Treasurer
    -0.08
    got
    -0.07
     timber
    -0.07
     ли
    -0.07
    Pou
    -0.07
    دۇ
    -0.07
     ves
    -0.07
    �
    -0.07
     opini
    -0.07
     aust
    -0.07
    POSITIVE LOGITS
     feststellen
    0.11
     causada
    0.09
     aanleiding
    0.08
     festgestellt
    0.08
     caused
    0.08
    ∆
    0.08
     ஏற்பட்ட
    0.08
    roy
    0.08
     ઘણ
    0.07
     ocurrido
    0.07
    Activations Density 0.016%

    No Known Activations