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. 11948
    Prev
    Next
    INDEX
    Explanations

    superconductors

    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
    pectral
    -0.09
    sequ
    -0.09
    mist
    -0.08
     efforts
    -0.08
    initions
    -0.08
    成人
    -0.08
    segment
    -0.08
     jaarlijkse
    -0.08
     sequencing
    -0.08
     노력
    -0.08
    POSITIVE LOGITS
     superconduct
    0.14
     الفلسطيني
    0.08
     vort
    0.08
     też
    0.08
     मर
    0.08
     цер
    0.08
     सुपर
    0.08
    _SC
    0.08
     पस
    0.08
     Cf
    0.07
    Activations Density 0.002%

    No Known Activations