© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64952
    Prev
    Next
    INDEX
    Explanations

    Greek letters, stars

    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
     ترت
    -0.08
     detox
    -0.08
     در
    -0.08
     دە
    -0.08
     Mystery
    -0.08
    ஸ
    -0.08
     قدم
    -0.08
     traff
    -0.08
     وسائل
    -0.07
     indemn
    -0.07
    POSITIVE LOGITS
     rov
    0.08
     Draco
    0.08
     Hz
    0.08
    \r
    0.07
     CV
    0.07
     volleyball
    0.07
    ž
    0.07
    Hz
    0.07
     CN
    0.07
     systems
    0.07
    Activations Density 0.003%

    No Known Activations