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. 112997
    Prev
    Next
    INDEX
    Explanations

    solution

    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
     prices
    -0.08
    Configs
    -0.08
     hentai
    -0.08
    动漫
    -0.08
     cosplay
    -0.08
     indik
    -0.08
     '{"
    -0.08
    ffects
    -0.08
     влияет
    -0.08
     oček
    -0.08
    POSITIVE LOGITS
     proofs
    0.11
     rigorous
    0.11
     proof
    0.10
    Proof
    0.10
     elegantly
    0.10
     Elegant
    0.09
     Proof
    0.09
     circumvent
    0.09
     élég
    0.09
     elegant
    0.09
    Activations Density 0.048%

    No Known Activations