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

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 130965
    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_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _IC
    -0.08
     المست
    -0.08
    aved
    -0.07
    �
    -0.07
    valuable
    -0.07
    �
    -0.07
    以上
    -0.07
    Ey
    -0.07
     Fundamentals
    -0.07
     gone
    -0.07
    POSITIVE LOGITS
     Athena
    0.08
    783
    0.08
     iom
    0.07
     Elevated
    0.07
    558
    0.07
     Dong
    0.07
     atuar
    0.07
    middleware
    0.07
     Während
    0.07
     Tae
    0.07
    Activations Density 0.026%

    No Known Activations