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. 97968
    Prev
    Next
    INDEX
    Explanations

    Website core vitals

    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
    κόσ
    -0.09
     grö
    -0.08
    pués
    -0.08
     VARIABLE
    -0.08
     OVER
    -0.08
     suht
    -0.08
     JOption
    -0.08
     ASK
    -0.08
     ondernem
    -0.08
     wheel
    -0.08
    POSITIVE LOGITS
    em
    0.08
    CP
    0.08
    サイト
    0.08
    utan
    0.08
    iquant
    0.08
     siti
    0.07
    cp
    0.07
     Site
    0.07
     Lot
    0.07
    Site
    0.07
    Activations Density 0.000%

    No Known Activations