© 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. 1200
    Prev
    Next
    INDEX
    Explanations

    mixing

    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
    ിരിക്കുന്ന
    -0.08
     raped
    -0.08
     rapper
    -0.08
     Lans
    -0.08
     hiss
    -0.08
     gás
    -0.07
     curb
    -0.07
     burns
    -0.07
     heroin
    -0.07
     lans
    -0.07
    POSITIVE LOGITS
     conventions
    0.08
    oints
    0.07
     incorrect
    0.07
     explanations
    0.07
    इ
    0.07
     confusing
    0.07
    efs
    0.07
     Expl
    0.07
     confl
    0.07
     tr
    0.07
    Activations Density 0.006%

    No Known Activations