© 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 EvalsExportsinterp-engineNEWAPI 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. 114157
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
     cognitive
    -0.08
     αποκ
    -0.08
     sufficiently
    -0.07
     við
    -0.07
     actualmente
    -0.07
     desired
    -0.07
     dichiar
    -0.07
     gelen
    -0.07
     Cognitive
    -0.07
     collaborative
    -0.07
    POSITIVE LOGITS
    细
    0.11
    _DETAIL
    0.10
     تفاصيل
    0.10
    _detail
    0.10
     détails
    0.10
     деталей
    0.09
     детали
    0.09
     волос
    0.09
    detail
    0.09
     Details
    0.09
    Activations Density 0.017%

    No Known Activations