© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 13185
    Prev
    Next
    INDEX
    Explanations

    告

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    万
    -0.09
     Vid
    -0.09
    Vid
    -0.09
     JES
    -0.08
     万
    -0.08
     Bell
    -0.08
     Madness
    -0.07
    hood
    -0.07
     rib
    -0.07
     insulation
    -0.07
    POSITIVE LOGITS
    Dept
    0.07
     compte
    0.07
    _department
    0.07
     없다
    0.07
     cherche
    0.07
     kuma
    0.07
    Cher
    0.07
    deadline
    0.07
     cher
    0.07
    Departamento
    0.07
    Activations Density 0.001%

    No Known Activations