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. 117525
    Prev
    Next
    INDEX
    Explanations

    Speaking aloud

    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
    ڪ
    -0.09
    ikhathi
    -0.07
     outlook
    -0.07
    -0.07
    lc
    -0.07
    гел
    -0.07
     Tao
    -0.07
     MOS
    -0.07
     kerberos
    -0.07
    replacement
    -0.07
    POSITIVE LOGITS
     rue
    0.09
     Saint
    0.08
    -speaking
    0.07
    /st
    0.07
     kroppen
    0.07
     꾸
    0.07
     উঠে
    0.07
     வந்து
    0.07
     Stimmen
    0.07
     듣
    0.07
    Activations Density 0.001%

    No Known Activations