© 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. 103155
    Prev
    Next
    INDEX
    Explanations

    citizen

    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
     несмотря
    -0.10
     내부
    -0.09
    内幕
    -0.09
    狠
    -0.09
     관련
    -0.08
     Hispanic
    -0.08
     abusive
    -0.08
     русский
    -0.08
     Spanish
    -0.08
     malgré
    -0.08
    POSITIVE LOGITS
     citizens
    0.14
     communal
    0.13
     cidadãos
    0.13
     citoyens
    0.12
     ciudadanos
    0.12
     citizen
    0.11
     beings
    0.11
     holog
    0.11
    Citizen
    0.10
    全民
    0.10
    Activations Density 0.043%

    No Known Activations