© 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. 13323
    Prev
    Next
    INDEX
    Explanations

    午

    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
     hole
    -0.08
     kui
    -0.08
    133
    -0.08
    -match
    -0.07
    Нач
    -0.07
     nasional
    -0.07
     mad
    -0.07
    IRT
    -0.07
     Pach
    -0.07
     mog
    -0.07
    POSITIVE LOGITS
    ới
    0.08
     �
    0.08
     �
    0.07
    ilte
    0.07
    ழ
    0.07
     خب
    0.07
    ತನ
    0.07
    ાળા
    0.07
     вперед
    0.07
     evenings
    0.07
    Activations Density 0.000%

    No Known Activations