© 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. 97415
    Prev
    Next
    INDEX
    Explanations

    1700s

    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
     we
    -0.08
    ್ಯಕ್ಷ
    -0.08
    iliy
    -0.08
     verhind
    -0.07
     модел
    -0.07
     lefel
    -0.07
    ujemo
    -0.07
     hablamos
    -0.07
    ્રણ
    -0.07
    こんにちは
    -0.07
    POSITIVE LOGITS
    .TIME
    0.11
    _TIME
    0.10
    时间
    0.10
     TIME
    0.09
     समय
    0.09
    時間
    0.09
     시간이
    0.09
     시간
    0.09
    _time
    0.09
    subst
    0.09
    Activations Density 0.008%

    No Known Activations