© 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. 64316
    Prev
    Next
    INDEX
    Explanations

    intake

    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
     existem
    -0.08
     Nort
    -0.08
    achtige
    -0.07
     Yor
    -0.07
     Tal
    -0.07
     dal
    -0.07
     Ton
    -0.07
     Sta
    -0.07
    ishes
    -0.07
    ತ್ತರ
    -0.07
    POSITIVE LOGITS
    sep
    0.09
    uyen
    0.08
    aca
    0.08
     dislike
    0.07
    asyon
    0.07
     Philipp
    0.07
     fenó
    0.07
     Pho
    0.07
     constituents
    0.07
    目前
    0.07
    Activations Density 0.003%

    No Known Activations