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. 75996
    Prev
    Next
    INDEX
    Explanations

    terms

    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
     morality
    -0.08
    смен
    -0.08
    JG
    -0.07
    是真的
    -0.07
     morals
    -0.07
     Gras
    -0.07
     Mujer
    -0.07
    =#
    -0.07
    iji
    -0.07
     justiça
    -0.07
    POSITIVE LOGITS
    თვის
    0.08
     those
    0.08
     تلك
    0.08
     gesam
    0.07
     desarroll
    0.07
     acestea
    0.07
    those
    0.07
    νω
    0.07
     там
    0.07
     õ
    0.07
    Activations Density 0.013%

    No Known Activations