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

    Neuronpedia

    Jacobian LensNEW
    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. 112735
    Prev
    Next
    INDEX
    Explanations

    hydrogen

    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
    验
    -0.09
    伍
    -0.09
     audiovis
    -0.08
     prow
    -0.08
     выстав
    -0.08
     intertw
    -0.08
     remuneration
    -0.08
     fruition
    -0.08
    人物
    -0.08
    扶贫
    -0.08
    POSITIVE LOGITS
    -rich
    0.09
    sd
    0.08
     sulfate
    0.07
     SD
    0.07
    SD
    0.07
     Extensive
    0.07
     sulf
    0.07
    Binary
    0.07
    واس
    0.07
    _strdup
    0.07
    Activations Density 0.001%

    No Known Activations