© 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. 1135
    Prev
    Next
    INDEX
    Explanations

    for

    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
    优秀
    -0.08
     diseases
    -0.07
    296
    -0.07
    ruption
    -0.07
     excellent
    -0.07
     확대
    -0.07
     ingenuity
    -0.07
    ėt
    -0.07
    ucing
    -0.07
     flaws
    -0.07
    POSITIVE LOGITS
     الح
    0.08
     parr
    0.08
     operativo
    0.08
     operate
    0.08
     ح
    0.07
     המ
    0.07
     Jenna
    0.07
     Yo
    0.07
     couches
    0.07
     socials
    0.07
    Activations Density 0.012%

    No Known Activations