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. 102789
    Prev
    Next
    INDEX
    Explanations

    Characteristics of services

    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
    -0.08
    (handles
    -0.08
     motivated
    -0.08
    -0.08
    lein
    -0.07
     arrangements
    -0.07
    ibo
    -0.07
    YA
    -0.07
     branch
    -0.07
     daarin
    -0.07
    POSITIVE LOGITS
     discount
    0.08
     Apex
    0.08
    ฯ
    0.08
     Superstar
    0.07
    discount
    0.07
    ⭐⭐
    0.07
     зал
    0.07
     nossas
    0.07
     必
    0.07
    (Storage
    0.07
    Activations Density 0.001%

    No Known Activations