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. 112031
    Prev
    Next
    INDEX
    Explanations

    legal arguments and court

    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
    Stepper
    -0.08
    created
    -0.08
    _lon
    -0.08
    soft
    -0.08
    lon
    -0.07
    Lon
    -0.07
    Soft
    -0.07
    Activ
    -0.07
    .la
    -0.07
    _soft
    -0.07
    POSITIVE LOGITS
    现场
    0.11
    双方
    0.10
     firsthand
    0.10
     हित
    0.10
     convain
    0.09
     সাক্ষ
    0.09
    алт
    0.09
     testimon
    0.09
     듣
    0.09
     testimony
    0.09
    Activations Density 0.018%

    No Known Activations