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. 130836
    Prev
    Next
    INDEX
    Explanations

    Foreign language text

    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
    ile
    -0.08
    itzat
    -0.07
    izado
    -0.07
     real
    -0.07
    mouse
    -0.07
    izas
    -0.07
    iają
    -0.07
     mouse
    -0.07
    wile
    -0.07
     dic
    -0.07
    POSITIVE LOGITS
    える
    0.12
    えて
    0.10
    نوع
    0.09
    届け
    0.09
    え
    0.09
    逃
    0.09
    送りします
    0.08
     দিলে
    0.08
    守
    0.08
    েট
    0.08
    Activations Density 0.000%

    No Known Activations