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. 29923
    Prev
    Next
    INDEX
    Explanations

    ~

    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
     attent
    -0.09
     deer
    -0.08
     asynchronous
    -0.08
     объем
    -0.08
     ID
    -0.08
     tät
    -0.08
     attachments
    -0.08
     performance
    -0.07
    =size
    -0.07
     معرف
    -0.07
    POSITIVE LOGITS
     temperatures
    0.10
     habitantes
    0.09
    800
    0.09
     temperaturen
    0.09
     Temperaturen
    0.09
     ताप
    0.08
     inhabitants
    0.08
     Пот
    0.08
    จัด
    0.08
    Earth
    0.08
    Activations Density 0.010%

    No Known Activations