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. 111549
    Prev
    Next
    INDEX
    Explanations

    partial

    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
    -0.07
     Gul
    -0.07
    Meu
    -0.07
     Pueblo
    -0.07
     gul
    -0.07
     Ihren
    -0.07
     मिलेगा
    -0.07
    標
    -0.07
    (Log
    -0.07
    würd
    -0.07
    POSITIVE LOGITS
     Maxwell
    0.09
    dele
    0.09
    /full
    0.08
     incom
    0.08
     Sommer
    0.07
     dele
    0.07
    స
    0.07
     Som
    0.07
     Jahres
    0.07
    imali
    0.07
    Activations Density 0.010%

    No Known Activations