© 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. 19-RESID-POST-AA
    11. 103055
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     silencio
    -0.07
     ganha
    -0.07
     obedient
    -0.07
     unimagin
    -0.07
     seeker
    -0.07
     seekers
    -0.07
    Clean
    -0.07
     Clean
    -0.07
     econômico
    -0.06
     被
    -0.06
    POSITIVE LOGITS
     аҟны
    0.09
     ахь
    0.09
    áne
    0.09
     écht
    0.09
    交流群
    0.09
    ʻota
    0.09
    eden
    0.08
     ప్రస్తుతం
    0.08
    Currently
    0.08
     오전
    0.08
    Activations Density 0.000%

    No Known Activations