© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48149
    Prev
    Next
    INDEX
    Explanations

    schema markup

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (username
    -0.10
    .Messages
    -0.09
    文件
    -0.09
    线程
    -0.09
    短信
    -0.09
     tablas
    -0.09
     tabla
    -0.09
    .xlsx
    -0.09
     tropas
    -0.09
    九九
    -0.09
    POSITIVE LOGITS
    Person
    0.12
    _place
    0.11
    Place
    0.11
    Organization
    0.11
     owl
    0.11
    organization
    0.11
    Thing
    0.10
    Corpor
    0.10
    Organisation
    0.10
    .place
    0.10
    Activations Density 0.018%

    No Known Activations