© 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. 19-RESID-POST-AA
    11. 102510
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     卓越
    -0.08
    atok
    -0.08
    >`;↵
    -0.08
    icron
    -0.07
    ның
    -0.07
    μεριν
    -0.07
     国产
    -0.07
    -0.07
     beeld
    -0.07
    ғат
    -0.07
    POSITIVE LOGITS
    "B
    0.08
    How
    0.08
    Descrição
    0.08
    Beschrijving
    0.07
    (bg
    0.07
    urch
    0.07
    Ihe
    0.07
     yaptı
    0.07
    Bg
    0.07
    Filt
    0.07
    Activations Density 0.000%
    No Known Activations