© 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. 48677
    Prev
    Next
    INDEX
    Explanations

    Russian text

    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
     żeby
    -0.14
     그냥
    -0.13
     그래서
    -0.13
     trzeba
    -0.13
     maybe
    -0.13
     trochę
    -0.12
    看看
    -0.12
     vibes
    -0.12
     coś
    -0.12
     veggies
    -0.12
    POSITIVE LOGITS
     посредством
    0.18
     различных
    0.17
     предприятий
    0.16
     Российской
    0.16
     sowie
    0.15
     вслед
    0.15
     населения
    0.15
     функциони
    0.15
     Республики
    0.15
     serta
    0.15
    Activations Density 0.083%

    No Known Activations