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. 112096
    Prev
    Next
    INDEX
    Explanations

    Social media, institutions

    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
     decom
    -0.08
     experien
    -0.08
     součas
    -0.08
    <Float
    -0.08
    轴
    -0.07
     tre
    -0.07
    Grouped
    -0.07
    <Tuple
    -0.07
    oten
    -0.07
     symmetrical
    -0.07
    POSITIVE LOGITS
     hashtag
    0.13
    微博
    0.11
     ट्विटर
    0.11
     livestream
    0.10
     hashtags
    0.10
     tweeting
    0.10
     ट्वीट
    0.10
     tweet
    0.10
    hashtags
    0.10
     tweeted
    0.10
    Activations Density 0.145%

    No Known Activations