© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68119
    Prev
    Next
    INDEX
    Explanations

    fairy

    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
    rico
    -0.07
     searching
    -0.07
     rat
    -0.07
     contempt
    -0.07
    383
    -0.07
     MCA
    -0.07
    其次
    -0.07
    _VISIBLE
    -0.07
     teasing
    -0.07
    Caching
    -0.07
    POSITIVE LOGITS
     സര്
    0.08
     dinner
    0.08
    ourd
    0.08
     Academia
    0.08
     Ipsum
    0.08
     Unser
    0.08
    -п
    0.08
    監
    0.08
    .Write
    0.08
     microbi
    0.08
    Activations Density 0.001%

    No Known Activations