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. 53877
    Prev
    Next
    INDEX
    Explanations

    software code

    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
    vc
    -0.08
    adge
    -0.08
    pag
    -0.08
     union
    -0.08
     Serviços
    -0.07
    astream
    -0.07
    Pag
    -0.07
     Quiz
    -0.07
    pong
    -0.07
    ocab
    -0.07
    POSITIVE LOGITS
     Double
    0.08
     Male
    0.08
     Female
    0.08
     betr
    0.08
     güz
    0.08
    Female
    0.08
    Commodity
    0.08
     Fem
    0.08
     Last
    0.08
     dopp
    0.08
    Activations Density 0.001%

    No Known Activations