© 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 EvalsExportsinterp-engineNEWAPI 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. 70642
    Prev
    Next
    INDEX
    Explanations

    greetings

    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
    .rest
    -0.07
    kwal
    -0.07
     helpen
    -0.07
    camel
    -0.07
     publico
    -0.07
    είς
    -0.07
     hardcover
    -0.07
    .Maximum
    -0.07
    ్బ
    -0.07
    holen
    -0.07
    POSITIVE LOGITS
     exchanged
    0.09
     Rak
    0.08
    itory
    0.07
    posición
    0.07
     പ്രക
    0.07
     inorganic
    0.07
    -ak
    0.07
     Committee
    0.07
     সবাই
    0.07
    とも
    0.07
    Activations Density 0.007%

    No Known Activations