© 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. 63799
    Prev
    Next
    INDEX
    Explanations

    News/social media context

    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
     enfer
    -0.08
     QA
    -0.08
    :nil
    -0.08
     talking
    -0.07
     Saying
    -0.07
    _MC
    -0.07
     affiliated
    -0.07
     diciendo
    -0.07
     winters
    -0.07
    ระดับ
    -0.07
    POSITIVE LOGITS
     aftermath
    0.10
    _peng
    0.09
     worldwide
    0.09
     Reuters
    0.09
     발표
    0.08
     انتشار
    0.08
    Reuters
    0.08
     الجاري
    0.08
     controversy
    0.08
    amine
    0.08
    Activations Density 0.202%

    No Known Activations