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. 55041
    Prev
    Next
    INDEX
    Explanations

    pulse

    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
    .Size
    -0.07
    .Text
    -0.07
     requ
    -0.07
    .Character
    -0.07
     available
    -0.07
    ...↵↵
    -0.07
     rout
    -0.07
     tradition
    -0.07
     distr
    -0.07
     der
    -0.07
    POSITIVE LOGITS
     cuadrados
    0.09
    /]
    0.09
     shouted
    0.09
     SHOULD
    0.08
     Oxygen
    0.08
     Successfully
    0.08
     restarted
    0.08
     abogados
    0.08
     bombas
    0.08
    Paused
    0.08
    Activations Density 0.001%

    No Known Activations