Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76799
    Prev
    Next
    INDEX
    Explanations

    staying updated on trends/news

    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
    性质
    -0.08
    OBS
    -0.08
    扫描
    -0.08
     parad
    -0.07
    -0.07
     trag
    -0.07
     repr
    -0.07
     CL
    -0.07
     BASIC
    -0.07
     peaceful
    -0.07
    POSITIVE LOGITS
    资讯
    0.10
     abre
    0.10
     subscribe
    0.09
     informiert
    0.09
    最新
    0.09
    了解
    0.09
    -informed
    0.09
     atualização
    0.09
     জানতে
    0.08
    领先
    0.08
    Activations Density 0.042%

    No Known Activations