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. 56247
    Prev
    Next
    INDEX
    Explanations

    论

    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
     laden
    -0.08
     mo
    -0.08
     ec
    -0.07
     Ec
    -0.07
     handed
    -0.07
     dabei
    -0.07
    ની
    -0.07
     compens
    -0.07
     discretionary
    -0.07
     fatt
    -0.07
    POSITIVE LOGITS
    霸
    0.09
    setter
    0.08
    ership
    0.07
    orship
    0.07
    究
    0.07
     Shu
    0.07
    사이트
    0.07
     вок
    0.07
     kasvat
    0.07
    aski
    0.07
    Activations Density 0.005%

    No Known Activations