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. 11829
    Prev
    Next
    INDEX
    Explanations

    site

    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
    142
    -0.08
    �
    -0.07
    働
    -0.07
    901
    -0.07
    700
    -0.07
    117
    -0.07
    析
    -0.07
     sembl
    -0.07
    697
    -0.07
    692
    -0.07
    POSITIVE LOGITS
    附近
    0.09
     excav
    0.08
     સ્થળ
    0.08
     নির্ব
    0.08
     Excav
    0.08
    ાંત
    0.08
    -location
    0.08
     evacuated
    0.08
     Mariana
    0.08
     oner
    0.08
    Activations Density 0.015%

    No Known Activations