Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 67345
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    _camera
    -0.09
    Museum
    -0.09
     museums
    -0.09
    (Camera
    -0.09
    Sensors
    -0.09
    _shader
    -0.09
     cinemat
    -0.09
    qml
    -0.09
     sensors
    -0.09
    采购
    -0.09
    POSITIVE LOGITS
     passwd
    0.12
     password
    0.12
     пароль
    0.12
     Passwort
    0.10
     LDAP
    0.10
    _PASSWORD
    0.10
    .Password
    0.10
     senha
    0.10
     ldap
    0.10
     PASSWORD
    0.10
    Activations Density 0.008%

    No Known Activations