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. 98280
    Prev
    Next
    INDEX
    Explanations

    Sales and automation tools

    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
    ış
    -0.09
     paul
    -0.08
    313
    -0.08
    oria
    -0.07
     epsilon
    -0.07
     dua
    -0.07
    ini
    -0.07
    reb
    -0.07
     �
    -0.07
    aryana
    -0.07
    POSITIVE LOGITS
    .Drawable
    0.08
     autom
    0.08
     nisl
    0.08
     vriend
    0.08
    Decrypt
    0.08
     gaten
    0.08
    .Deserialize
    0.08
    Decode
    0.08
     desapar
    0.08
     leukste
    0.07
    Activations Density 0.000%

    No Known Activations