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. 60840
    Prev
    Next
    INDEX
    Explanations

    2

    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
     Ritual
    -0.10
     ritual
    -0.10
     Morocco
    -0.08
     metodo
    -0.08
     Metodo
    -0.08
    	vo
    -0.08
     orin
    -0.08
     Martin
    -0.07
     Turns
    -0.07
     धर
    -0.07
    POSITIVE LOGITS
    일보
    0.07
     FDP
    0.07
     appraisal
    0.07
     FB
    0.07
    Grande
    0.07
     entail
    0.07
     batteries
    0.06
    etchup
    0.06
     erlaub
    0.06
     д
    0.06
    Activations Density 0.062%

    No Known Activations