© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12876
    Prev
    Next
    INDEX
    Explanations

    plus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пов
    -0.07
    por
    -0.07
    泡
    -0.07
    armony
    -0.07
     chỉnh
    -0.07
    unnan
    -0.07
     Baş
    -0.07
    cli
    -0.07
    ملكة
    -0.07
    -0.07
    POSITIVE LOGITS
     han
    0.08
     Federation
    0.08
     jej
    0.08
     án
    0.07
     fear
    0.07
     cons
    0.07
     jü
    0.07
     threatened
    0.07
    ాది
    0.07
     hor
    0.07
    Activations Density 0.002%

    No Known Activations