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. 119317
    Prev
    Next
    INDEX
    Explanations

    math, calculations, numbers

    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
     municipality
    -0.08
     Municipality
    -0.08
    一家
    -0.07
    chia
    -0.07
     trá
    -0.07
     Parcelable
    -0.07
     midpoint
    -0.07
     formulated
    -0.07
    dg
    -0.07
    isement
    -0.07
    POSITIVE LOGITS
     meios
    0.09
     dimensão
    0.08
    _BITS
    0.08
    СТ
    0.08
     logarith
    0.08
     Engineers
    0.08
    Hvis
    0.08
    -log
    0.08
     Layers
    0.08
    层
    0.08
    Activations Density 0.016%

    No Known Activations