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. 106014
    Prev
    Next
    INDEX
    Explanations

    data transfer speeds

    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
    слом
    -0.10
    _outline
    -0.09
    慎
    -0.09
     anxious
    -0.09
     booklet
    -0.08
    อล
    -0.08
     considerate
    -0.08
     argumentative
    -0.08
     apolog
    -0.08
     विच
    -0.08
    POSITIVE LOGITS
     bandwidth
    0.14
     Ethernet
    0.13
     Mbps
    0.13
     throughput
    0.13
    Bandwidth
    0.13
     baud
    0.12
    Mbps
    0.12
     ethernet
    0.11
     MHz
    0.11
     capability
    0.11
    Activations Density 0.019%

    No Known Activations