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. 30711
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     north
    -0.08
     inget
    -0.08
     Cro
    -0.08
     muab
    -0.07
     להצ
    -0.07
     elo
    -0.07
     tanke
    -0.07
     ukup
    -0.07
     angene
    -0.07
     acces
    -0.07
    POSITIVE LOGITS
    사진
    0.09
     lun
    0.08
    ىلى
    0.08
    īk
    0.07
    리
    0.07
    िरी
    0.07
     storms
    0.07
    摄
    0.07
    allows
    0.07
    ák
    0.07
    Activations Density 0.066%

    No Known Activations