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. 49083
    Prev
    Next
    INDEX
    Explanations

    English language

    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
     gpu
    -0.08
     Juven
    -0.08
     Lenin
    -0.08
    นคร
    -0.07
     Mwan
    -0.07
     expo
    -0.07
     ganzen
    -0.07
     adc
    -0.07
     cuda
    -0.07
     Benito
    -0.07
    POSITIVE LOGITS
     lyric
    0.08
     English
    0.08
    izi
    0.08
     eget
    0.08
    English
    0.08
     Engeland
    0.08
    Adventure
    0.08
    英语
    0.07
     영어
    0.07
    DIY
    0.07
    Activations Density 0.015%

    No Known Activations