© 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. 48510
    Prev
    Next
    INDEX
    Explanations

    non-english, immediate action

    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
     vastly
    -0.08
     naturally
    -0.07
     parem
    -0.07
     heavily
    -0.07
    xef
    -0.07
     radically
    -0.07
     sanction
    -0.07
    bold
    -0.07
     brothers
    -0.07
     easily
    -0.07
    POSITIVE LOGITS
     즉
    0.30
    即
    0.27
    立
    0.26
    �
    0.24
     即
    0.23
    ，即
    0.23
     马
    0.21
    馬
    0.20
     உட
    0.20
     tức
    0.19
    Activations Density 0.030%

    No Known Activations