© 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. 68878
    Prev
    Next
    INDEX
    Explanations

    the

    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
    厚
    -0.08
    ರ
    -0.08
    中新网
    -0.08
     הנש
    -0.07
     ನರ
    -0.07
     жок
    -0.07
    حف
    -0.07
     выт
    -0.07
    �
    -0.07
     мороз
    -0.07
    POSITIVE LOGITS
    /im
    0.08
     direttamente
    0.08
     ultime
    0.08
    rxjs
    0.08
     आर्थिक
    0.08
     jsx
    0.07
    vidence
    0.07
     dernier
    0.07
     positiv
    0.07
    /run
    0.07
    Activations Density 0.000%

    No Known Activations