© 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. 129084
    Prev
    Next
    INDEX
    Explanations

    drove

    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
    важа
    -0.07
    עש
    -0.07
     wollen
    -0.07
    stander
    -0.07
    output
    -0.07
    sex
    -0.07
     verwe
    -0.07
    standers
    -0.07
    EV
    -0.07
    schuld
    -0.07
    POSITIVE LOGITS
    Away
    0.10
     hacia
    0.10
     Away
    0.09
     away
    0.09
     juntos
    0.08
     вперед
    0.08
     tillbaka
    0.08
    (":
    0.08
     назад
    0.08
     hypocrisy
    0.08
    Activations Density 0.022%

    No Known Activations