© 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. 15-RESID-POST-AA
    11. 16368
    Prev
    Next
    INDEX
    Explanations

    power functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crypto
    -0.08
     Horizon
    -0.07
     surrounding
    -0.07
     forwarding
    -0.07
     Wünsche
    -0.07
     recursion
    -0.07
     strtok
    -0.07
     resurf
    -0.07
     highlighted
    -0.07
     equivalent
    -0.07
    POSITIVE LOGITS
    表达
    0.09
     слож
    0.08
    ’avons
    0.08
     необы
    0.08
    ’association
    0.08
    自由
    0.08
    .float
    0.08
     italic
    0.08
    复杂
    0.08
     exprim
    0.08
    Activations Density 0.003%

    No Known Activations