© 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. 30462
    Prev
    Next
    INDEX
    Explanations

    initial

    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
    لی
    -0.08
    گاه
    -0.07
    러운
    -0.07
     Tas
    -0.07
    ительно
    -0.07
     protr
    -0.07
     uplift
    -0.07
     mét
    -0.07
     verein
    -0.07
     gerecht
    -0.07
    POSITIVE LOGITS
    ITUDE
    0.08
    itude
    0.08
    ನ್
    0.08
     Arb
    0.07
     Nd
    0.07
    碰
    0.07
    /features
    0.07
    IDTH
    0.07
     Amin
    0.07
     collisions
    0.07
    Activations Density 0.001%

    No Known Activations