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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98087
    Prev
    Next
    INDEX
    Explanations

    Foreign language text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moder
    -0.07
     :=
    -0.07
    制作
    -0.07
    40
    -0.07
    :=
    -0.07
     locaux
    -0.07
    于
    -0.07
     mód
    -0.07
     :
    -0.07
    用
    -0.07
    POSITIVE LOGITS
     Gior
    0.09
    ต้องฝาก
    0.09
     ntxiv
    0.09
    흥
    0.09
    pargne
    0.09
     शेयर
    0.09
     сур
    0.09
     Sana
    0.09
     المباد
    0.08
     Għ
    0.08
    Activations Density 0.000%

    No Known Activations