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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110403
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    عا
    -0.08
    782
    -0.08
     reflect
    -0.08
     replace
    -0.07
    .music
    -0.07
     upon
    -0.07
    =p
    -0.07
    icrobial
    -0.07
    =n
    -0.07
    AEC
    -0.07
    POSITIVE LOGITS
     Kiss
    0.08
    érieures
    0.08
     vel
    0.08
    iseerde
    0.08
     Kin
    0.08
     ವಾಹ
    0.08
    chnik
    0.07
     Dock
    0.07
     Condom
    0.07
     буд
    0.07
    Activations Density 0.064%

    No Known Activations