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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75456
    Prev
    Next
    INDEX
    Explanations

    Arithmetic problems

    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
    ুপ
    -0.08
    山市
    -0.07
    ତ
    -0.07
    imson
    -0.07
     and
    -0.07
     as
    -0.07
    itative
    -0.07
     I
    -0.07
     placeholder
    -0.07
     installment
    -0.07
    POSITIVE LOGITS
     начинается
    0.10
     يبدأ
    0.10
     بدأ
    0.10
     بدء
    0.10
    starts
    0.10
     commencer
    0.10
     comienzo
    0.10
     ആരംഭ
    0.10
     comien
    0.10
     begint
    0.09
    Activations Density 0.093%

    No Known Activations