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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29847
    Prev
    Next
    INDEX
    Explanations

    translation

    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
     literacy
    -0.09
     Literacy
    -0.09
     സ്വീകര
    -0.09
     التمو
    -0.08
    ീറ്റ
    -0.08
     الاستثمار
    -0.08
    ൊഴ
    -0.08
     പരീക്ഷ
    -0.08
    ALLOC
    -0.08
     allocate
    -0.08
    POSITIVE LOGITS
     hops
    0.09
    wend
    0.08
     fini
    0.08
    erus
    0.08
     billi
    0.08
    richten
    0.08
    byen
    0.07
     cáps
    0.07
     pathname
    0.07
     cinc
    0.07
    Activations Density 0.005%

    No Known Activations