© 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. 13052
    Prev
    Next
    INDEX
    Explanations

    out

    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
     Meng
    -0.08
     Melt
    -0.08
     ifad
    -0.08
     Anderson
    -0.08
     pathname
    -0.08
     mechanically
    -0.07
     الر
    -0.07
     melt
    -0.07
    egg
    -0.07
    Meng
    -0.07
    POSITIVE LOGITS
    饭
    0.08
    wow
    0.08
     coping
    0.08
     valued
    0.07
     Serv
    0.07
     INF
    0.07
     <$
    0.07
    敬
    0.07
     בהם
    0.07
     ethos
    0.07
    Activations Density 0.007%

    No Known Activations