© 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. 3-RESID-POST-AA
    11. 13310
    Prev
    Next
    INDEX
    Explanations

    ins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pies
    -0.08
    ови
    -0.08
    Tod
    -0.08
    logo
    -0.07
     creep
    -0.07
    -Val
    -0.07
    _IC
    -0.07
    /icon
    -0.07
     quest
    -0.07
     Urs
    -0.07
    POSITIVE LOGITS
    ই
    0.08
     Deals
    0.08
     Deal
    0.08
     WH
    0.08
    卫
    0.07
     Gustav
    0.07
     Stephan
    0.07
     விழ
    0.07
     ACA
    0.07
     соп
    0.07
    Activations Density 0.001%

    No Known Activations