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. 12280
    Prev
    Next
    INDEX
    Explanations

    casual

    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
    ‍റെ
    -0.08
    어서
    -0.08
    Bre
    -0.07
     уп
    -0.07
     Eugene
    -0.07
     Elevator
    -0.07
    Kr
    -0.07
     Kind
    -0.07
     plaats
    -0.07
     Login
    -0.07
    POSITIVE LOGITS
    .imp
    0.08
    mente
    0.08
    യായി
    0.08
    각
    0.08
     mosaic
    0.08
    用品
    0.08
    ifiable
    0.07
     perpetrators
    0.07
    intel
    0.07
     stroll
    0.07
    Activations Density 0.003%

    No Known Activations