© 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. 1144
    Prev
    Next
    INDEX
    Explanations

    docking

    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
     चाहते
    -0.07
    ных
    -0.07
     euren
    -0.07
     dives
    -0.07
     व्य
    -0.07
     अपने
    -0.07
    iente
    -0.07
     आपके
    -0.07
    ccan
    -0.06
     divided
    -0.06
    POSITIVE LOGITS
     Fortress
    0.09
    immutable
    0.08
     මා
    0.08
    Stephen
    0.08
     lixo
    0.08
    SEA
    0.08
    BOX
    0.08
     bato
    0.08
     minimo
    0.08
    ADM
    0.08
    Activations Density 0.001%

    No Known Activations