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. 74627
    Prev
    Next
    INDEX
    Explanations

    Life

    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
     justific
    -0.07
     negotiated
    -0.07
    טע
    -0.07
    א
    -0.07
     onto
    -0.07
     договора
    -0.07
    פט
    -0.07
     fick
    -0.07
     justa
    -0.07
     корр
    -0.07
    POSITIVE LOGITS
     stages
    0.12
     стад
    0.11
    Stages
    0.11
    阶段
    0.11
     стадии
    0.11
     nurturing
    0.11
     larvae
    0.10
     مراحل
    0.10
    生命周期
    0.10
     phases
    0.10
    Activations Density 0.010%

    No Known Activations