© 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. 847
    Prev
    Next
    INDEX
    Explanations

    [

    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
     Acc
    -0.08
     que
    -0.08
     in
    -0.07
     unl
    -0.07
     with
    -0.07
    (Transaction
    -0.07
     Dam
    -0.07
    oji
    -0.07
    -0.07
    (UInt
    -0.07
    POSITIVE LOGITS
     endings
    0.08
    .third
    0.08
     shout
    0.08
     şekl
    0.08
     ********
    0.08
     شر
    0.08
    .parts
    0.08
     الم
    0.08
     sonidos
    0.08
     ataupun
    0.08
    Activations Density 0.003%

    No Known Activations