© 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. 7-RESID-POST-AA
    11. 1005
    Prev
    Next
    INDEX
    Explanations

    eyes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commencé
    -0.08
     fractions
    -0.07
     переб
    -0.07
     flown
    -0.07
     gestern
    -0.07
     fahr
    -0.07
     кр
    -0.07
    伙
    -0.07
    昨
    -0.07
     затрат
    -0.07
    POSITIVE LOGITS
     সাল
    0.09
     accented
    0.08
     hashtag
    0.08
     enfat
    0.07
     tomb
    0.07
    elder
    0.07
    (tuple
    0.07
    ires
    0.07
     peripheral
    0.07
     MER
    0.07
    Activations Density 0.006%

    No Known Activations