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. 106043
    Prev
    Next
    INDEX
    Explanations

    tire

    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
     potential
    -0.07
     prolong
    -0.07
     currency
    -0.07
     한
    -0.07
     yap
    -0.07
     header
    -0.07
     defect
    -0.07
    한
    -0.07
     likely
    -0.07
     considering
    -0.07
    POSITIVE LOGITS
    idro
    0.09
    ้วย
    0.08
    iew
    0.08
     lwe
    0.08
    。今年
    0.08
     masyarakat
    0.08
     mastur
    0.08
    ALUE
    0.08
    ijkl
    0.08
    ิติ
    0.08
    Activations Density 0.000%

    No Known Activations