© 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. 19-RESID-POST-AA
    11. 20332
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.09
     or
    -0.08
    200
    -0.08
    199
    -0.08
    uan
    -0.08
    cemos
    -0.08
     in
    -0.08
    201
    -0.07
    анди
    -0.07
    600
    -0.07
    POSITIVE LOGITS
     uitge
    0.09
    ينه
    0.09
     ניצ
    0.08
     NOTHING
    0.08
     رفض
    0.08
    ំហំ
    0.08
     consisted
    0.08
    Beschrijving
    0.08
     مجرد
    0.08
     بودند
    0.08
    Activations Density 0.000%

    No Known Activations