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. 12237
    Prev
    Next
    INDEX
    Explanations

    Script

    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
     George
    -0.08
    837
    -0.07
    l
    -0.07
    held
    -0.07
    (p
    -0.07
    244
    -0.07
     Karl
    -0.07
    _k
    -0.07
    _f
    -0.07
     Berger
    -0.07
    POSITIVE LOGITS
    脚
    0.12
    腳
    0.12
     Script
    0.12
     scripts
    0.11
     scripting
    0.11
     script
    0.11
     SCRIPT
    0.11
     Scripts
    0.11
    .Script
    0.11
    .script
    0.11
    Activations Density 0.004%

    No Known Activations