© 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. 99720
    Prev
    Next
    INDEX
    Explanations

    past tense/participle

    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
     ì
    -0.08
     happen
    -0.08
     İn
    -0.08
     chéad
    -0.08
     पहल
    -0.08
     ohere
    -0.08
     оқ
    -0.08
     Gateway
    -0.07
     onafh
    -0.07
     nò
    -0.07
    POSITIVE LOGITS
    อยู่
    0.12
     อยู่
    0.11
    状態
    0.11
    ydessä
    0.10
     состоянии
    0.10
    状态
    0.10
     alive
    0.10
     상태
    0.09
     ready
    0.09
    ready
    0.09
    Activations Density 0.388%

    No Known Activations