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

    Neuronpedia

    Jacobian LensNEW
    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. 113414
    Prev
    Next
    INDEX
    Explanations

    palm

    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
    bv
    -0.09
    Kol
    -0.08
     coalition
    -0.08
     Rudy
    -0.07
    AMS
    -0.07
    عمل
    -0.07
     Bish
    -0.07
     Paris
    -0.07
     viện
    -0.07
     Ress
    -0.07
    POSITIVE LOGITS
     grind
    0.08
    estic
    0.08
     Scots
    0.08
    体现
    0.07
     celular
    0.07
     Touchable
    0.07
    握
    0.07
    -touch
    0.07
     dren
    0.07
    心
    0.07
    Activations Density 0.004%

    No Known Activations