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. 65287
    Prev
    Next
    INDEX
    Explanations

    immersion

    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
     provo
    -0.08
     represented
    -0.08
    -
    -0.07
    trate
    -0.07
     constructed
    -0.07
    ,-
    -0.07
    iq
    -0.07
    azard
    -0.07
     =================================
    -0.07
             ↵
    -0.07
    POSITIVE LOGITS
     herramientas
    0.08
     earbuds
    0.08
    .ham
    0.08
     outils
    0.08
     screwdriver
    0.08
     ès
    0.08
     Operators
    0.07
     साध
    0.07
    matically
    0.07
     podp
    0.07
    Activations Density 0.001%

    No Known Activations