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. 7-RESID-POST-AA
    6. 130990
    Prev
    Next
    INDEX
    Explanations

    date and time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Indo
    -0.08
    部
    -0.08
     disadvantage
    -0.08
     foss
    -0.08
    (Optional
    -0.08
    viri
    -0.07
     procure
    -0.07
     proprio
    -0.07
     장
    -0.07
    ਿੱ�
    -0.07
    POSITIVE LOGITS
     Val
    0.09
    -valu
    0.09
    Val
    0.09
     valuation
    0.08
    ounen
    0.08
    valu
    0.08
     Benz
    0.08
     Townsend
    0.08
     Reinh
    0.08
     lenses
    0.07
    Activations Density 0.004%

    No Known Activations