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. 13006
    Prev
    Next
    INDEX
    Explanations

    mang

    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
    qui
    -0.09
    qrt
    -0.08
     рел
    -0.07
    qrst
    -0.07
     нос
    -0.07
     Pierce
    -0.07
     pronounce
    -0.07
     над
    -0.07
     texts
    -0.07
    idered
    -0.07
    POSITIVE LOGITS
     groundwork
    0.09
     proteção
    0.09
     vegetation
    0.08
     ಬೇ
    0.08
     tightening
    0.08
     Cruc
    0.08
    Zh
    0.08
    vironment
    0.08
     വേ
    0.08
    夹
    0.08
    Activations Density 0.001%

    No Known Activations