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. 88335
    Prev
    Next
    INDEX
    Explanations

    Positive sentiment

    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
     hon
    -0.08
     ɗ
    -0.08
    Hon
    -0.08
     jack
    -0.08
    hon
    -0.08
     NCC
    -0.07
    low
    -0.07
     surrounding
    -0.07
    .modify
    -0.07
    ਵੀ
    -0.07
    POSITIVE LOGITS
     nicely
    0.08
     caractér
    0.07
     adorable
    0.07
    ,这是
    0.07
     Sala
    0.07
     glad
    0.07
     sederhana
    0.07
    !
    0.07
     neat
    0.07
     Sei
    0.07
    Activations Density 0.019%

    No Known Activations