© 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. 48095
    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
    ue
    -0.10
    -search
    -0.08
    künfte
    -0.08
    -arm
    -0.08
    itations
    -0.08
     ветер
    -0.07
    ুঁ
    -0.07
    ueva
    -0.07
    ueira
    -0.07
     বাংল
    -0.07
    POSITIVE LOGITS
    орами
    0.10
    ред
    0.10
    оров
    0.09
    ором
    0.09
    ора
    0.09
    оре
    0.08
    редит
    0.08
    орам
    0.08
    оры
    0.08
    之一
    0.08
    Activations Density 0.001%

    No Known Activations