© 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. 91661
    Prev
    Next
    INDEX
    Explanations

    destroy

    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
    工
    -0.08
    никам
    -0.07
     наш
    -0.07
     therapists
    -0.07
     compute
    -0.07
    .interfaces
    -0.07
     tortured
    -0.07
     obligations
    -0.07
     formulate
    -0.07
    zag
    -0.07
    POSITIVE LOGITS
    Disappear
    0.11
     Removal
    0.11
    _Remove
    0.11
     حذف
    0.11
     удаления
    0.11
    Removal
    0.11
     removal
    0.11
     remov
    0.11
    .Remove
    0.10
     Removes
    0.10
    Activations Density 0.003%

    No Known Activations