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. 112462
    Prev
    Next
    INDEX
    Explanations

    Dates, ages, and years

    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
    ník
    -0.08
     groundwork
    -0.08
    umfang
    -0.08
    lapping
    -0.08
    iyak
    -0.08
    :inline
    -0.08
     alongside
    -0.07
     defendants
    -0.07
    regel
    -0.07
     الأساسي
    -0.07
    POSITIVE LOGITS
     dimens
    0.09
     unlucky
    0.08
     plausible
    0.08
    Alt
    0.08
    甜
    0.08
    dimensions
    0.08
     plaus
    0.08
    寓
    0.08
     yerl
    0.08
     annuelle
    0.08
    Activations Density 0.014%

    No Known Activations