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. 11-RESID-POST-AA
    6. 43899
    Prev
    Next
    INDEX
    Explanations

    colons

    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
     ಪೂ
    -0.09
     material
    -0.07
    zens
    -0.07
     ವ್ಯಾಪ
    -0.07
    Turn
    -0.07
     ಬಳ
    -0.07
    educ
    -0.07
    _turn
    -0.07
     ಕಾರ
    -0.07
     Turn
    -0.07
    POSITIVE LOGITS
     parece
    0.10
     يبدو
    0.09
     неправиль
    0.09
     scheint
    0.09
     Parece
    0.09
     incorrect
    0.09
     fehlt
    0.09
     sembra
    0.09
     dato
    0.09
     personenbez
    0.09
    Activations Density 0.135%

    No Known Activations