© 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. 23-RESID-POST-AA
    11. 6301
    Prev
    Next
    INDEX
    Explanations

    compilation, compiling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afric
    -0.09
     Africa
    -0.08
     Ethiopian
    -0.08
     ýaşa
    -0.08
     durmu
    -0.08
     Airt
    -0.08
     ענ
    -0.08
    აფ
    -0.08
     חודשים
    -0.08
     África
    -0.08
    POSITIVE LOGITS
     compilation
    0.52
     compile
    0.52
     compiling
    0.51
     Compile
    0.50
    Compile
    0.50
     compiler
    0.49
     Compilation
    0.49
    Compilation
    0.49
     compil
    0.49
    compile
    0.48
    Activations Density 0.104%

    No Known Activations