© 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. 31507
    Prev
    Next
    INDEX
    Explanations

    cross-origin

    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
    (letter
    -0.09
     featuring
    -0.08
    忠
    -0.08
     mọ
    -0.07
    င်
    -0.07
     fog
    -0.07
     сов
    -0.07
     LED
    -0.07
     regular
    -0.07
    ųjų
    -0.07
    POSITIVE LOGITS
     नीति
    0.09
    -policy
    0.09
     नेत
    0.08
     estamp
    0.08
     eat
    0.08
     अनुमति
    0.08
     jelly
    0.08
     काफी
    0.08
    _policy
    0.08
    ्ड
    0.07
    Activations Density 0.001%

    No Known Activations