© 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. 23-RESID-POST-AA
    11. 5370
    Prev
    Next
    INDEX
    Explanations

    正

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ig
    -0.08
     cib
    -0.08
     Iris
    -0.08
    diti
    -0.08
    Ig
    -0.07
     liberation
    -0.07
    irar
    -0.07
     Ri
    -0.07
     iris
    -0.07
     gubern
    -0.07
    POSITIVE LOGITS
    向
    0.16
    念
    0.16
    面
    0.11
     面
    0.09
    olle
    0.08
    面对
    0.08
    Scrollable
    0.08
    面的
    0.08
    향
    0.08
     vectors
    0.08
    Activations Density 0.001%

    No Known Activations