© 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. 69753
    Prev
    Next
    INDEX
    Explanations

    Tetris code examples

    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
    маш
    -0.08
     accountable
    -0.08
     SDK
    -0.08
     respectful
    -0.08
     عام
    -0.07
    implement
    -0.07
     مخت
    -0.07
     Worc
    -0.07
     witnesses
    -0.07
     alternative
    -0.07
    POSITIVE LOGITS
     fullscreen
    0.09
    etris
    0.09
     llenar
    0.09
    .blocks
    0.09
    _FULLSCREEN
    0.08
     insertar
    0.08
     Kampf
    0.08
     заполн
    0.08
     вращ
    0.08
    fullscreen
    0.08
    Activations Density 0.004%

    No Known Activations