© 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. 15-RESID-POST-AA
    11. 16724
    Prev
    Next
    INDEX
    Explanations

    Math expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Madness
    -0.07
     ENS
    -0.07
    убеж
    -0.07
     Three
    -0.07
     Constructor
    -0.07
     AD
    -0.07
     سندس
    -0.07
    cams
    -0.07
    butikk
    -0.07
    کرا
    -0.07
    POSITIVE LOGITS
    》和
    0.11
     valamint
    0.10
     وكذلك
    0.10
    ”和
    0.09
     뿐
    0.09
     तसे
    0.09
     ಜೊ
    0.09
    뿐
    0.09
    》《
    0.09
     그리고
    0.09
    Activations Density 0.066%

    No Known Activations