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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 99096
    Prev
    Next
    INDEX
    Explanations

    radio communications

    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
     collagen
    -0.09
     remodeling
    -0.09
     handbags
    -0.09
    癌
    -0.08
     Remodeling
    -0.08
     दर्द
    -0.08
    يدي
    -0.08
    塑
    -0.08
    _embedding
    -0.08
    .fact
    -0.08
    POSITIVE LOGITS
     telegram
    0.11
     transmitter
    0.11
    MHz
    0.11
     Debian
    0.10
     outages
    0.10
     baud
    0.10
     rádio
    0.10
    PING
    0.10
     beep
    0.10
     ವಿದ್ಯ
    0.10
    Activations Density 0.017%

    No Known Activations