© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44323
    Prev
    Next
    INDEX
    Explanations

    sample

    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
     electric
    -0.08
     Electric
    -0.08
     الكهرب
    -0.08
     listrik
    -0.08
     eléctrico
    -0.08
     geleverd
    -0.08
    -electric
    -0.08
     الكهربائية
    -0.08
     beschermd
    -0.08
     terra
    -0.08
    POSITIVE LOGITS
     선정
    0.12
    名单
    0.11
     subset
    0.11
     randomly
    0.11
    Subset
    0.10
     subsets
    0.10
    Sampling
    0.10
    subset
    0.10
     sampling
    0.10
    _subset
    0.10
    Activations Density 0.016%

    No Known Activations