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. 112814
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ичным
    -0.08
     зак
    -0.08
     законом
    -0.08
     rencontré
    -0.08
    .Sp
    -0.07
     Negro
    -0.07
    Manip
    -0.07
     Manip
    -0.07
    falz
    -0.07
     horizontal
    -0.07
    POSITIVE LOGITS
     loa
    0.08
     వరకు
    0.08
     toneladas
    0.08
    ibration
    0.08
    まで
    0.07
     construcción
    0.07
    课程
    0.07
    enta
    0.07
    hema
    0.07
    טרה
    0.07
    Activations Density 0.079%

    No Known Activations