Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113063
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
     EMP
    -0.08
     starte
    -0.08
     lr
    -0.08
     gde
    -0.08
     όλοι
    -0.08
    czny
    -0.08
    ryk
    -0.08
     MH
    -0.08
    slam
    -0.07
     absorption
    -0.07
    POSITIVE LOGITS
    という
    0.10
    」という
    0.09
     అనే
    0.08
     ಎಂಬ
    0.08
     என்பது
    0.08
    。
    0.08
    fers
    0.07
     என்பதை
    0.07
    `↵↵
    0.07
     hydrochlor
    0.07
    Activations Density 0.061%

    No Known Activations