© 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. 3-RESID-POST-AA
    11. 13016
    Prev
    Next
    INDEX
    Explanations

    leafy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ضر
    -0.08
     sâu
    -0.08
     Levin
    -0.07
     eld
    -0.07
    refresh
    -0.07
     cu
    -0.07
    ဖြ
    -0.07
     constantly
    -0.07
    ucat
    -0.07
    .steps
    -0.07
    POSITIVE LOGITS
    Hw
    0.08
     ador
    0.08
     ог
    0.08
     simpat
    0.07
    zeichnis
    0.07
    -o
    0.07
     ಹಾಕ
    0.07
     diminu
    0.07
     Поп
    0.07
     aʻe
    0.07
    Activations Density 0.004%

    No Known Activations