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. 119798
    Prev
    Next
    INDEX
    Explanations

    calculations

    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
    йғур
    -0.11
     акыр
    -0.10
    �ირ
    -0.10
    иқи
    -0.10
    �ილ
    -0.10
    ინც
    -0.09
    иқат
    -0.09
    ирғ
    -0.09
    წუხ
    -0.09
    �ევნ
    -0.09
    POSITIVE LOGITS
     ??
    0.08
    80
    0.08
     !==
    0.07
    .astype
    0.07
     typ
    0.07
    Å
    0.07
    95
    0.07
    _zone
    0.07
    Ab
    0.07
    ਾਬ
    0.07
    Activations Density 0.108%

    No Known Activations