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. 60673
    Prev
    Next
    INDEX
    Explanations

    directly

    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
    CString
    -0.08
    Iterations
    -0.08
    (Bundle
    -0.08
    ൈ
    -0.07
    ൈറ്റ
    -0.07
     iterations
    -0.07
    Jes
    -0.07
    	bytes
    -0.07
    Hashtable
    -0.07
    .astype
    -0.07
    POSITIVE LOGITS
     east
    0.09
     west
    0.08
     northwest
    0.08
     kaya
    0.08
    ంటి
    0.08
     atop
    0.08
    258
    0.08
     perched
    0.08
     ux
    0.07
    ಟ್ಟಿ
    0.07
    Activations Density 0.009%

    No Known Activations