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. 65449
    Prev
    Next
    INDEX
    Explanations

    Should/pronouns

    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
    tium
    -0.08
     Mutex
    -0.08
     ağı
    -0.08
     Marg
    -0.08
    ``
    -0.07
    lihat
    -0.07
    ലയ
    -0.07
    muş
    -0.07
     defaultdict
    -0.07
    阴
    -0.07
    POSITIVE LOGITS
     gold
    0.09
     coaching
    0.09
     uniquely
    0.09
     우리
    0.08
     గురించి
    0.08
     అత్య
    0.08
    可信
    0.08
     என்பதை
    0.08
     તમારા
    0.08
     ఎంద
    0.08
    Activations Density 0.030%

    No Known Activations