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. 131009
    Prev
    Next
    INDEX
    Explanations

    calculations

    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
    ová
    -0.07
    Jacob
    -0.07
    che
    -0.07
    21
    -0.07
     minim
    -0.07
     Sør
    -0.07
    .Cloud
    -0.07
     Dylan
    -0.07
     Minim
    -0.07
    -0.07
    POSITIVE LOGITS
     terraza
    0.09
    �
    0.09
    �
    0.09
    GN
    0.08
     repl
    0.08
     dents
    0.08
    艾
    0.08
     mags
    0.08
     especiales
    0.08
    鑫
    0.07
    Activations Density 0.223%

    No Known Activations