© 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. 96846
    Prev
    Next
    INDEX
    Explanations

    market in other languages

    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
    weeted
    -0.08
     senha
    -0.07
    ottie
    -0.07
     skrif
    -0.07
     stylesheet
    -0.07
    leanor
    -0.07
    ployee
    -0.07
    >Password
    -0.07
     embroidery
    -0.07
    /thread
    -0.07
    POSITIVE LOGITS
     market
    0.79
    市场
    0.76
    Market
    0.72
     बाजार
    0.72
    市場
    0.71
     Market
    0.71
     시장
    0.70
     বাজার
    0.70
     mercado
    0.69
    _market
    0.67
    Activations Density 0.309%

    No Known Activations