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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12864
    Prev
    Next
    INDEX
    Explanations

    Negation/invalidity

    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
     Mam
    -0.08
     मुल
    -0.08
     الأسد
    -0.08
    阁
    -0.08
     نائب
    -0.08
    汗
    -0.07
     ват
    -0.07
     caretaker
    -0.07
     للق
    -0.07
     whey
    -0.07
    POSITIVE LOGITS
     происходит
    0.08
     transporting
    0.07
     kron
    0.07
     perse
    0.07
    ല്ല
    0.07
     INV
    0.07
    793
    0.07
    isku
    0.07
     sak
    0.07
     segue
    0.07
    Activations Density 0.000%

    No Known Activations