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. 11-RESID-POST-AA
    6. 11983
    Prev
    Next
    INDEX
    Explanations

    array

    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
     اسر
    -0.08
     конц
    -0.08
    面积
    -0.08
     äußerst
    -0.08
    æðum
    -0.08
     gemeinsamen
    -0.08
     gigant
    -0.08
    //
    ↵
    -0.08
    记录
    -0.08
    اشت
    -0.08
    POSITIVE LOGITS
     distro
    0.08
    _ENABLED
    0.08
    =M
    0.08
    =r
    0.08
     সচ
    0.07
    CAP
    0.07
    mb
    0.07
    -hard
    0.07
    _NONE
    0.07
    belongs
    0.07
    Activations Density 0.001%

    No Known Activations