© 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. 23-RESID-POST-AA
    11. 48649
    Prev
    Next
    INDEX
    Explanations

    Rates and taxes

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     importantes
    -0.08
    슬
    -0.08
     ganhar
    -0.07
     gagner
    -0.07
     bolster
    -0.07
    elik
    -0.07
    сли
    -0.07
    +='
    -0.07
     중요한
    -0.07
    viri
    -0.07
    POSITIVE LOGITS
     taux
    0.28
     tasa
    0.26
     نرخ
    0.25
     tasas
    0.25
     taxas
    0.24
     दर
    0.23
     rate
    0.22
     معدل
    0.22
     taxa
    0.21
     índice
    0.21
    Activations Density 0.030%

    No Known Activations