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. 98282
    Prev
    Next
    INDEX
    Explanations

    L

    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
     другое
    -0.09
     intellectually
    -0.08
    (before
    -0.08
     અભ
    -0.08
     män
    -0.07
    الت
    -0.07
     распространя
    -0.07
    ительное
    -0.07
    leten
    -0.07
    ині
    -0.07
    POSITIVE LOGITS
    istoire
    0.07
    0.07
     langkah
    0.07
    ians
    0.07
    owej
    0.07
    ulare
    0.07
    otp
    0.07
     seg
    0.07
    314
    0.07
    虽
    0.07
    Activations Density 0.000%

    No Known Activations