Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111782
    Prev
    Next
    INDEX
    Explanations

    indoor activities

    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
    ක්ෂ
    -0.07
    vm
    -0.07
    틴
    -0.07
    kr
    -0.07
    _vm
    -0.07
    Bytes
    -0.07
    	vm
    -0.07
    von
    -0.07
    cki
    -0.07
    Object
    -0.07
    POSITIVE LOGITS
     indoor
    0.14
     indoors
    0.11
    Indoor
    0.11
    空气
    0.11
     Indoor
    0.11
     air
    0.10
     помещений
    0.10
    保护
    0.10
     sheltered
    0.10
     एयर
    0.10
    Activations Density 0.060%

    No Known Activations