© 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. 11-RESID-POST-AA
    6. 47281
    Prev
    Next
    INDEX
    Explanations

    virtual environment setup

    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
     Henry
    -0.08
     orig
    -0.08
     entrepreneur
    -0.08
     CEO
    -0.08
     Rahul
    -0.07
     Schweizer
    -0.07
     Conversely
    -0.07
     Birch
    -0.07
     correctness
    -0.07
     businessman
    -0.07
    POSITIVE LOGITS
    -mounted
    0.10
     установлен
    0.09
    خابات
    0.09
     المحمولة
    0.09
    罩
    0.09
    ė
    0.09
    ildə
    0.08
    .dll
    0.08
    lts
    0.08
     встанов
    0.08
    Activations Density 0.001%

    No Known Activations