© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113112
    Prev
    Next
    INDEX
    Explanations

    best

    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
     सें
    -0.08
     spacecraft
    -0.08
     settembre
    -0.08
    rees
    -0.08
     permutations
    -0.08
     гект
    -0.08
    セン
    -0.08
    一区
    -0.07
    ��
    -0.07
     jednom
    -0.07
    POSITIVE LOGITS
     enjoyment
    0.08
     apprécier
    0.08
     apreciar
    0.08
     disfrutar
    0.08
     optimale
    0.07
    Enjoy
    0.07
    最佳
    0.07
     perte
    0.07
    recommended
    0.07
     Enjoy
    0.07
    Activations Density 0.011%

    No Known Activations