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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77890
    Prev
    Next
    INDEX
    Explanations

    stages

    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
    ým
    -0.09
    ential
    -0.08
    œur
    -0.08
    حل
    -0.08
    देश
    -0.08
    147
    -0.07
     Wald
    -0.07
     Giant
    -0.07
    acket
    -0.07
     sharper
    -0.07
    POSITIVE LOGITS
    阶段
    0.12
     этапе
    0.12
     etapas
    0.11
     stages
    0.11
     phases
    0.10
    -stage
    0.10
     этап
    0.10
     uncon
    0.09
     단계
    0.09
     стадии
    0.09
    Activations Density 0.021%

    No Known Activations