© 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. 25105
    Prev
    Next
    INDEX
    Explanations

    game mechanics

    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
     alarming
    -0.08
     곳
    -0.08
     부분
    -0.08
    728
    -0.07
    ckt
    -0.07
     repetitive
    -0.07
     gigantic
    -0.07
    pos
    -0.07
    계
    -0.07
     toko
    -0.07
    POSITIVE LOGITS
     Consume
    0.10
     ataque
    0.10
     સફળ
    0.10
     attaque
    0.09
     सफल
    0.09
     attaques
    0.09
     সফল
    0.09
     lykk
    0.09
     విజయ
    0.08
     miser
    0.08
    Activations Density 0.027%

    No Known Activations