© 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. 102831
    Prev
    Next
    INDEX
    Explanations

    empower

    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
    weil
    -0.09
    jara
    -0.09
    كون
    -0.08
     twee
    -0.08
    .jsoup
    -0.07
     tempting
    -0.07
    weet
    -0.07
    wera
    -0.07
     tlak
    -0.07
     Bedarf
    -0.07
    POSITIVE LOGITS
    ment
    0.17
     empowerment
    0.13
    ments
    0.12
    enment
    0.11
     empower
    0.11
    ­ment
    0.11
     empowers
    0.11
    MENT
    0.11
     Empower
    0.11
    મેન્ટ
    0.10
    Activations Density 0.004%

    No Known Activations