© 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. 113326
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     وا
    -0.08
     JFile
    -0.08
     électronique
    -0.07
     қолдан
    -0.07
     жас
    -0.07
     акт
    -0.07
     नियमित
    -0.07
     Massive
    -0.07
    .URL
    -0.07
    .activation
    -0.07
    POSITIVE LOGITS
     Diana
    0.09
     Cleopatra
    0.09
    fees
    0.08
     lop
    0.08
     lấy
    0.07
     bearish
    0.07
    125
    0.07
     memberi
    0.07
     destru
    0.07
    402
    0.07
    Activations Density 0.264%

    No Known Activations