© 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. 11-RESID-POST-AA
    11. 44575
    Prev
    Next
    INDEX
    Explanations

    别

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creates
    -0.08
     cria
    -0.08
     describe
    -0.07
     Create
    -0.07
    лод
    -0.07
     Cho
    -0.07
    소년
    -0.07
     étaient
    -0.07
     கொண்ட
    -0.07
     создать
    -0.07
    POSITIVE LOGITS
     despair
    0.12
     complac
    0.10
     misguided
    0.10
     panic
    0.09
     wees
    0.09
     tristeza
    0.09
     hesitate
    0.09
     забы
    0.09
     misconception
    0.09
    panic
    0.09
    Activations Density 0.040%

    No Known Activations