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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9165
    Prev
    Next
    INDEX
    Explanations

    heirlooms and inheritance

    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
    ui
    -0.08
     conducive
    -0.08
    ybrid
    -0.08
    .sponge
    -0.07
     pose
    -0.07
    .Block
    -0.07
     ui
    -0.07
    lean
    -0.07
    uib
    -0.07
     slope
    -0.07
    POSITIVE LOGITS
     heir
    0.11
     traditions
    0.11
     tradição
    0.11
     heritage
    0.10
     tradición
    0.10
     tradition
    0.10
     folklore
    0.09
     sentimental
    0.09
    递
    0.09
     خانو
    0.09
    Activations Density 0.017%

    No Known Activations