© 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. 108362
    Prev
    Next
    INDEX
    Explanations

    test page

    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
     rescued
    -0.08
     verified
    -0.07
     legalized
    -0.07
    Verified
    -0.07
    feer
    -0.07
     Chat
    -0.07
     suppression
    -0.07
     Protest
    -0.07
    ;n
    -0.07
     receptor
    -0.07
    POSITIVE LOGITS
    arput
    0.08
     صفحة
    0.08
    /password
    0.08
    arlugu
    0.08
    odnev
    0.08
    agaq
    0.08
     मस
    0.08
     წერ
    0.08
     drawable
    0.08
    ойти
    0.08
    Activations Density 0.002%

    No Known Activations