© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78222
    Prev
    Next
    INDEX
    Explanations

    multiple languages and unicode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (full
    -0.08
    (count
    -0.08
    (un
    -0.08
     independence
    -0.08
     rach
    -0.08
    �
    -0.08
    (Byte
    -0.08
    (Long
    -0.07
    (func
    -0.07
    (de
    -0.07
    POSITIVE LOGITS
    ̆
    0.08
    semos
    0.08
    velte
    0.07
    ৎ
    0.07
    pcion
    0.07
    ğa
    0.07
    vim
    0.07
    ̈
    0.07
    vind
    0.07
     ï
    0.07
    Activations Density 0.024%

    No Known Activations