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. 98678
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     cung
    -0.08
     ภาษา
    -0.08
    ктә
    -0.07
     scopes
    -0.07
     jid
    -0.07
    isper
    -0.07
     مذ
    -0.07
    crito
    -0.07
     Erstellung
    -0.07
     groep
    -0.07
    POSITIVE LOGITS
    Greater
    0.08
     Owens
    0.07
    Compr
    0.07
    ₪
    0.07
    ₹
    0.07
    Canada
    0.07
     greater
    0.07
     nulla
    0.07
     ή
    0.07
     сравнению
    0.07
    Activations Density 0.016%

    No Known Activations