© 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. 95072
    Prev
    Next
    INDEX
    Explanations

    art

    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
     kenn
    -0.08
    txn
    -0.08
     teadm
    -0.07
    ifty
    -0.07
    ұ
    -0.07
     ligging
    -0.07
     કેટલીક
    -0.07
    赶
    -0.07
    car
    -0.07
     yapı
    -0.07
    POSITIVE LOGITS
     studio
    0.08
    "D
    0.08
    ,D
    0.08
     Photoshop
    0.08
     DG
    0.08
     sme
    0.07
     ஓ
    0.07
    =D
    0.07
     ultraviolet
    0.07
     hoki
    0.07
    Activations Density 0.006%

    No Known Activations