© 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. 3-RESID-POST-AA
    11. 1022
    Prev
    Next
    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leonard
    -0.08
     Friedman
    -0.08
    撒
    -0.08
    Unsupported
    -0.08
     Acid
    -0.08
     undocumented
    -0.08
     YC
    -0.08
     Erk
    -0.08
     Lake
    -0.07
    sid
    -0.07
    POSITIVE LOGITS
    éal
    0.08
     tra
    0.08
     wizard
    0.08
     мек
    0.08
    tra
    0.07
    pref
    0.07
     связанные
    0.07
     cog
    0.07
    ấm
    0.07
    ৎস
    0.07
    Activations Density 0.217%

    No Known Activations