© 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. 7-RESID-POST-AA
    11. 859
    Prev
    Next
    INDEX
    Explanations

    choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeg
    -0.08
     Rever
    -0.08
     Requests
    -0.08
     продолж
    -0.07
     Axios
    -0.07
     Communities
    -0.07
     Aspir
    -0.07
    wane
    -0.07
    ricula
    -0.07
    lha
    -0.07
    POSITIVE LOGITS
     coincidence
    0.09
     nons
    0.09
    巧
    0.08
     coincid
    0.08
    embedding
    0.08
     catchy
    0.08
    .coin
    0.08
     যাতে
    0.08
    盒
    0.08
     coin
    0.08
    Activations Density 0.028%

    No Known Activations