© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18418
    Prev
    Next
    INDEX
    Explanations

    complex

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kèk
    -0.10
    ratulations
    -0.10
     vissa
    -0.09
     einigen
    -0.09
     కొన్ని
    -0.09
    იქრ
    -0.08
     ciertas
    -0.08
    �览
    -0.08
     certaines
    -0.08
    -0.08
    POSITIVE LOGITS
     complex
    0.27
    complex
    0.22
    复杂
    0.22
     complexo
    0.21
     Complex
    0.20
     komplex
    0.20
     complexe
    0.20
    Complex
    0.20
    _complex
    0.20
     multif
    0.20
    Activations Density 0.020%
    No Known Activations