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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78319
    Prev
    Next
    INDEX
    Explanations

    woman

    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
    资本
    -0.08
     ماده
    -0.08
     mpi
    -0.08
     george
    -0.08
     Defines
    -0.07
    市场
    -0.07
    治理
    -0.07
    .Undef
    -0.07
     traduc
    -0.07
     louis
    -0.07
    POSITIVE LOGITS
     BAG
    0.09
     Bram
    0.08
    rias
    0.08
     desperation
    0.08
     bathroom
    0.08
    Dropbox
    0.08
     at
    0.08
     arriving
    0.07
     INC
    0.07
     Crock
    0.07
    Activations Density 0.001%

    No Known Activations