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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 75999
    Prev
    Next
    INDEX
    Explanations

    term

    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
     soms
    -0.09
    timestamp
    -0.09
    _timestamp
    -0.09
    _TIMESTAMP
    -0.08
     মান
    -0.08
    Timestamp
    -0.08
    annot
    -0.08
    真实性
    -0.07
     timestamp
    -0.07
    ਅ
    -0.07
    POSITIVE LOGITS
     nachhaltig
    0.09
     Restoration
    0.09
     restoration
    0.09
     sustainably
    0.08
     galima
    0.08
     ambitious
    0.08
    建立
    0.08
     cin
    0.08
    �
    0.08
     Eventually
    0.08
    Activations Density 0.019%

    No Known Activations