© 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. 48665
    Prev
    Next
    INDEX
    Explanations

    verbs

    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
     выбира
    -0.16
     знаход
    -0.16
     pomaga
    -0.16
    станавли
    -0.15
    бира
    -0.15
     дода
    -0.15
    łąc
    -0.15
     умень
    -0.14
     wyb
    -0.14
     pomag
    -0.14
    POSITIVE LOGITS
     предоставить
    0.13
     создать
    0.13
     дать
    0.13
     выполнить
    0.13
     написать
    0.13
     сделать
    0.12
     изменить
    0.12
     назвать
    0.12
     открыть
    0.12
     найти
    0.12
    Activations Density 0.035%

    No Known Activations