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. 12297
    Prev
    Next
    INDEX
    Explanations

    Colombia

    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
     hwnd
    -0.10
     wills
    -0.08
     Buh
    -0.08
     dialogs
    -0.08
    .arm
    -0.08
     diejenigen
    -0.08
     арм
    -0.08
    ىلى
    -0.08
     Arlington
    -0.08
     Dies
    -0.08
    POSITIVE LOGITS
     Colombia
    0.11
     Colombian
    0.09
     colomb
    0.09
    taken
    0.09
     Bogotá
    0.08
    otp
    0.08
     colombiano
    0.08
    tr
    0.08
    _tr
    0.08
    _emb
    0.08
    Activations Density 0.009%

    No Known Activations