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

    Neuronpedia

    Jacobian LensNEW
    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. 112353
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     Russo
    -0.08
    ишь
    -0.08
    orld
    -0.08
     kamera
    -0.08
    ikbaar
    -0.08
     penggunaan
    -0.08
    .naming
    -0.08
    otyping
    -0.08
     cheering
    -0.07
    ились
    -0.07
    POSITIVE LOGITS
     Mutex
    0.08
    Mutex
    0.08
    _mutex
    0.08
    _PTR
    0.07
     schwer
    0.07
     hardness
    0.07
     الاقتصادية
    0.07
    hard
    0.07
     سخت
    0.07
    _disk
    0.07
    Activations Density 0.005%

    No Known Activations