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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 31456
    Prev
    Next
    INDEX
    Explanations

    start

    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
     ING
    -0.08
     مهما
    -0.08
    yllic
    -0.08
    peyan
    -0.08
    illery
    -0.08
     നിയ
    -0.07
    ador
    -0.07
    ignant
    -0.07
    rawn
    -0.07
    itve
    -0.07
    POSITIVE LOGITS
     sorun
    0.08
    問題
    0.08
     issues
    0.08
    Proble
    0.08
     dopo
    0.07
     cuestiones
    0.07
     мәсел
    0.07
     Gep
    0.07
     implications
    0.07
    279
    0.07
    Activations Density 0.000%

    No Known Activations