© 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. 1078
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Hel
    -0.08
    pic
    -0.08
     Circuit
    -0.08
    Pic
    -0.07
     hel
    -0.07
     Chester
    -0.07
    Cable
    -0.07
     Bally
    -0.07
    RJ
    -0.07
     helic
    -0.07
    POSITIVE LOGITS
    끔
    0.09
    vidia
    0.08
    traits
    0.08
     shadows
    0.07
     inflated
    0.07
     tane
    0.07
     tunne
    0.07
     بعدما
    0.07
     Ramirez
    0.07
     الأحيان
    0.07
    Activations Density 0.000%

    No Known Activations