© 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. 26017
    Prev
    Next
    INDEX
    Explanations

    variable assignments

    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
    ®,
    -0.08
     mos
    -0.08
    enti
    -0.07
    ®
    -0.07
    ™,
    -0.07
     deutlich
    -0.07
     nett
    -0.07
     ubu
    -0.07
    誌
    -0.07
     Shelby
    -0.07
    POSITIVE LOGITS
    代表
    0.08
    马上
    0.08
     revival
    0.08
     revive
    0.08
     register
    0.08
    ímica
    0.07
    represent
    0.07
    rogate
    0.07
     personales
    0.07
     resultant
    0.07
    Activations Density 0.023%

    No Known Activations