© 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. 64782
    Prev
    Next
    INDEX
    Explanations

    Cutting through/ piercing

    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
    onga
    -0.08
     వై
    -0.07
     depende
    -0.07
    Recycler
    -0.07
     repert
    -0.07
     référ
    -0.07
    rollers
    -0.07
     इस्त
    -0.07
    utenção
    -0.07
    wach
    -0.07
    POSITIVE LOGITS
     sharply
    0.08
     ambiental
    0.08
     ambientales
    0.08
    ပ
    0.08
     ambientais
    0.08
     Ambiental
    0.07
    мен
    0.07
    hell
    0.07
    �
    0.07
     mè
    0.07
    Activations Density 0.010%

    No Known Activations