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. 98687
    Prev
    Next
    INDEX
    Explanations

    .

    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
    mm
    -0.08
    इ
    -0.08
    -0.08
     vient
    -0.08
    vgl
    -0.08
     meaningless
    -0.08
    ümüzde
    -0.08
    sb
    -0.07
    sold
    -0.07
    ब
    -0.07
    POSITIVE LOGITS
    /topics
    0.08
     अनुस
    0.08
    ages
    0.08
     rule
    0.07
     vuoksi
    0.07
     cleaner
    0.07
    onik
    0.07
     Br
    0.07
     roub
    0.07
     نظ
    0.07
    Activations Density 0.002%

    No Known Activations