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. 54283
    Prev
    Next
    INDEX
    Explanations

    pick or choose

    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
     제대로
    -0.08
     만드는
    -0.07
     }));↵
    -0.07
    proper
    -0.07
     કરવાની
    -0.07
    Hoe
    -0.07
    maps
    -0.07
    ')));↵
    -0.07
    Quad
    -0.07
     AO
    -0.07
    POSITIVE LOGITS
     tack
    0.08
     konse
    0.08
     रिस
    0.08
     wholeheartedly
    0.08
     Streaming
    0.07
     hierfür
    0.07
     Christianity
    0.07
     curto
    0.07
     spi
    0.07
     spelled
    0.07
    Activations Density 0.012%

    No Known Activations