© 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. 94440
    Prev
    Next
    INDEX
    Explanations

    Questions with numerical values

    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
     правил
    -0.08
    awu
    -0.07
     itse
    -0.07
     지
    -0.07
    ుమ
    -0.07
    .mn
    -0.07
     dood
    -0.07
    BASEPATH
    -0.07
    सू
    -0.07
     pace
    -0.07
    POSITIVE LOGITS
     Lid
    0.09
    ค์
    0.08
     Bij
    0.07
    披
    0.07
     பாட
    0.07
    {-#
    0.07
     તેમણે
    0.07
    ง
    0.07
     Kuv
    0.07
     Nij
    0.07
    Activations Density 0.053%

    No Known Activations