© 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. 47727
    Prev
    Next
    INDEX
    Explanations

    password input

    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
    (bus
    -0.09
    omány
    -0.08
    公交
    -0.08
    促进
    -0.08
     фестив
    -0.08
     examines
    -0.08
    alformed
    -0.08
     appealed
    -0.08
    æg
    -0.08
     thrive
    -0.08
    POSITIVE LOGITS
     password
    0.17
    password
    0.15
     passwords
    0.15
    Password
    0.15
    _password
    0.15
    (password
    0.14
     Password
    0.14
    密码
    0.14
    .Password
    0.13
    .password
    0.13
    Activations Density 0.003%

    No Known Activations