© 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. 43044
    Prev
    Next
    INDEX
    Explanations

    ping

    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
    REET
    -0.08
    biet
    -0.08
     coats
    -0.08
     borderline
    -0.08
    Recurring
    -0.07
     cosmetics
    -0.07
     toothpaste
    -0.07
     wel
    -0.07
    =============
    -0.07
     admi
    -0.07
    POSITIVE LOGITS
    一下
    0.09
    击
    0.08
     Traveler
    0.07
     Ami
    0.07
     dulce
    0.07
     Duke
    0.07
     Boca
    0.07
    nud
    0.07
    觉
    0.07
    _he
    0.07
    Activations Density 0.005%

    No Known Activations