Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130798
    Prev
    Next
    INDEX
    Explanations

    Code and foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     сюжет
    -0.10
     client's
    -0.09
    nee
    -0.08
    	Client
    -0.08
    Л
    -0.08
    客户端
    -0.08
    ր
    -0.08
    004
    -0.08
     कथा
    -0.08
    �
    -0.08
    POSITIVE LOGITS
     yma
    0.08
     એસ
    0.08
     അസ
    0.08
     quý
    0.08
     yacc
    0.08
    cesse
    0.08
     Rational
    0.08
     Century
    0.08
     Shelton
    0.07
     GCC
    0.07
    Activations Density 0.002%

    No Known Activations