© 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. 11-RESID-POST-AA
    11. 99582
    Prev
    Next
    INDEX
    Explanations

    vehicle leasing

    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
    .once
    -0.08
     einstellen
    -0.08
    -clean
    -0.07
     insertion
    -0.07
     নেতা
    -0.07
    .freeze
    -0.07
    Island
    -0.07
    -invasive
    -0.07
    -not
    -0.07
    Chicken
    -0.07
    POSITIVE LOGITS
     സോഷ്യ
    0.08
     Shadow
    0.08
     SOB
    0.08
     ブラック
    0.08
     shadow
    0.08
     社
    0.08
    698
    0.07
     Skinny
    0.07
     φωτο
    0.07
     Nissan
    0.07
    Activations Density 0.005%

    No Known Activations