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. 76816
    Prev
    Next
    INDEX
    Explanations

    chain

    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
     jq
    -0.09
     Bukkit
    -0.09
     Dangerous
    -0.09
    �
    -0.08
     WPA
    -0.08
     Vim
    -0.08
     jw
    -0.08
     binocular
    -0.08
     sécurité
    -0.08
     bedoeling
    -0.08
    POSITIVE LOGITS
    物流
    0.17
     logistics
    0.15
     Logistics
    0.13
    配送
    0.13
     logistical
    0.13
     logística
    0.12
    运输
    0.11
    _pipeline
    0.11
     freight
    0.10
     procurement
    0.10
    Activations Density 0.016%

    No Known Activations