© 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. 11-RESID-POST-AA
    11. 44367
    Prev
    Next
    INDEX
    Explanations

    symmetric difference

    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
     dims
    -0.07
    -session
    -0.07
    dims
    -0.07
     Param
    -0.07
     param
    -0.07
     infusion
    -0.07
    agger
    -0.07
     drainage
    -0.07
     aann
    -0.07
    -dro
    -0.07
    POSITIVE LOGITS
     bip
    0.09
     рада
    0.08
     círculo
    0.08
     XOR
    0.08
     symmetric
    0.08
    дары
    0.08
     rozd
    0.08
    진
    0.08
     زوج
    0.08
     کالا
    0.08
    Activations Density 0.007%

    No Known Activations