Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65109
    Prev
    Next
    INDEX
    Explanations

    Russian suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refugee
    -0.09
    /function
    -0.08
     refugees
    -0.08
    ెన్
    -0.08
     Refuge
    -0.07
    Wann
    -0.07
    kne
    -0.07
     extrater
    -0.07
     demonstr
    -0.07
     Wann
    -0.07
    POSITIVE LOGITS
    反馈
    0.09
     feedback
    0.08
     reverse
    0.08
     March
    0.08
     Reverse
    0.08
    298
    0.08
    属
    0.07
    reverse
    0.07
    .reverse
    0.07
     Mail
    0.07
    Activations Density 0.008%

    No Known Activations