© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69933
    Prev
    Next
    INDEX
    Explanations

    Entering

    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
     شروط
    -0.08
     Lighthouse
    -0.07
     Pharm
    -0.07
    Employer
    -0.07
    .container
    -0.07
     existente
    -0.07
     Employer
    -0.07
     Pharma
    -0.07
     Laguna
    -0.07
     Employers
    -0.07
    POSITIVE LOGITS
    阶段
    0.10
     стадии
    0.10
     regime
    0.10
     مرحلة
    0.09
    时期
    0.09
     этап
    0.09
     مرحله
    0.09
     transition
    0.09
     tahap
    0.09
     adolescence
    0.09
    Activations Density 0.064%

    No Known Activations