© 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 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. 42987
    Prev
    Next
    INDEX
    Explanations

    palindromes and numbers

    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
     déliv
    -0.08
     yakın
    -0.08
     Deliver
    -0.08
     delivering
    -0.08
     entregar
    -0.07
     దగ్గ
    -0.07
    Deliver
    -0.07
     farmers
    -0.07
     decentralized
    -0.07
     Farmers
    -0.07
    POSITIVE LOGITS
     interno
    0.10
     الداخلي
    0.09
     internos
    0.09
    -body
    0.08
    _body
    0.08
    SECOND
    0.08
    સ્મ
    0.08
     internas
    0.08
    áns
    0.08
    ส่วน
    0.08
    Activations Density 0.032%

    No Known Activations