© 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. 45664
    Prev
    Next
    INDEX
    Explanations

    main/master

    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
     Concord
    -0.07
     mauvais
    -0.07
     bogus
    -0.07
     অসম
    -0.07
     Excess
    -0.07
     அந்த
    -0.07
     dunia
    -0.07
     MW
    -0.07
     freedoms
    -0.07
     doubtful
    -0.07
    POSITIVE LOGITS
    :Int
    0.08
    DUCTION
    0.08
    {EIF
    0.08
    -policy
    0.08
    യിലെ
    0.08
    åk
    0.07
     काल
    0.07
     policy
    0.07
     verantwort
    0.07
    iyyət
    0.07
    Activations Density 0.002%

    No Known Activations