© 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. 99827
    Prev
    Next
    INDEX
    Explanations

    2

    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
     ka
    -0.09
     toner
    -0.08
     miteinander
    -0.08
    范
    -0.08
    .fix
    -0.08
    .body
    -0.08
     cak
    -0.08
    ાભ
    -0.08
     meme
    -0.07
     طبي
    -0.07
    POSITIVE LOGITS
     único
    0.08
    Unique
    0.08
     única
    0.08
    ày
    0.08
     únicos
    0.08
    unique
    0.08
    _unique
    0.07
     uniqueness
    0.07
     solt
    0.07
    ्य
    0.07
    Activations Density 0.001%

    No Known Activations