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. 48374
    Prev
    Next
    INDEX
    Explanations

    steel cage

    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
    شي
    -0.08
    ായ
    -0.08
     своей
    -0.07
    Formatting
    -0.07
     Uso
    -0.07
     antiguo
    -0.07
    uario
    -0.07
    bao
    -0.07
     വ്യാപ
    -0.07
     قط
    -0.07
    POSITIVE LOGITS
     desse
    0.08
     atta
    0.08
     Floating
    0.08
     najbolj
    0.08
     esse
    0.08
    ांक
    0.08
     furnished
    0.08
     Arbitration
    0.08
     Ange
    0.08
    &r
    0.08
    Activations Density 0.001%

    No Known Activations