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. 77517
    Prev
    Next
    INDEX
    Explanations

    Generating detailed plans instructions

    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
    Enabled
    -0.08
    .domain
    -0.08
    _enabled
    -0.07
     guaranteed
    -0.07
     assured
    -0.07
    (domain
    -0.07
    .pol
    -0.07
    Guaranteed
    -0.07
     definitive
    -0.07
    .ready
    -0.07
    POSITIVE LOGITS
    拆
    0.10
     subdivisions
    0.10
     sub
    0.10
     подраздел
    0.09
     Detail
    0.09
     yder
    0.09
    enumer
    0.09
     ઉપલ
    0.09
    DETAIL
    0.09
    返水
    0.09
    Activations Density 0.020%

    No Known Activations