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. 11719
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ablemente
    -0.08
     baggage
    -0.08
    aced
    -0.08
     dobro
    -0.08
     mises
    -0.08
    PRISE
    -0.08
    aciju
    -0.08
     begleitet
    -0.08
     Victoria
    -0.08
    vidos
    -0.08
    POSITIVE LOGITS
    而言
    0.07
     nucle
    0.07
    	flag
    0.07
    univers
    0.07
     telefo
    0.07
     invert
    0.07
     Trie
    0.07
     شنا
    0.07
     Shuffle
    0.07
    	false
    0.07
    Activations Density 0.018%

    No Known Activations