© 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. 54503
    Prev
    Next
    INDEX
    Explanations

    Law

    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
     rookie
    -0.08
    +
    -0.08
    TOP
    -0.08
    inca
    -0.08
    .↵↵
    -0.08
     ianao
    -0.08
     STATUS
    -0.08
    inių
    -0.07
     undefined
    -0.07
     років
    -0.07
    POSITIVE LOGITS
     safeguard
    0.11
     accountable
    0.10
     incentiv
    0.10
     geschaffen
    0.09
     accountability
    0.09
     safeguarding
    0.09
     incentivar
    0.09
    ساهم
    0.09
     deterr
    0.09
    公平
    0.09
    Activations Density 0.140%

    No Known Activations