© 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. 47658
    Prev
    Next
    INDEX
    Explanations

    image prompting

    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
     the
    -0.08
    :↵
    -0.08
    ى
    -0.07
     언제
    -0.07
    ಟ್ಟು
    -0.07
     Förderung
    -0.07
     lectures
    -0.07
    (records
    -0.07
     Fernando
    -0.06
    وريا
    -0.06
    POSITIVE LOGITS
     möglichst
    0.10
    jes
    0.09
     Suitable
    0.08
    unders
    0.08
     uniquement
    0.08
     સામ
    0.08
     polished
    0.08
    .fact
    0.08
     suitable
    0.08
     বাক
    0.08
    Activations Density 0.024%

    No Known Activations