© 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. 108184
    Prev
    Next
    INDEX
    Explanations

    survivor

    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
    _ads
    -0.09
    ച്ച
    -0.08
     recess
    -0.08
     adag
    -0.08
     Lauf
    -0.07
    _pixel
    -0.07
    _null
    -0.07
     детал
    -0.07
     rigor
    -0.07
    drops
    -0.07
    POSITIVE LOGITS
    ёи
    0.08
     Joi
    0.08
    欢
    0.08
     होकर
    0.08
     टी
    0.08
     Yank
    0.08
    sex
    0.08
     eftir
    0.08
     sexism
    0.08
     acknowledge
    0.08
    Activations Density 0.004%

    No Known Activations