© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45627
    Prev
    Next
    INDEX
    Explanations

    Racing/Formula 1

    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
    رافق
    -0.09
    ू
    -0.08
    .invalid
    -0.08
     पहुंचे
    -0.08
     나온
    -0.08
    停止
    -0.08
     HEAD
    -0.08
    出版
    -0.08
     gericht
    -0.08
     예약
    -0.08
    POSITIVE LOGITS
     stable
    0.08
    Makes
    0.07
     tactical
    0.07
     hotspot
    0.07
     bumper
    0.07
     cs
    0.07
     prone
    0.07
    ifty
    0.07
    VARIABLE
    0.07
    stable
    0.07
    Activations Density 0.017%

    No Known Activations