© 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. 78225
    Prev
    Next
    INDEX
    Explanations

    AA

    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
    -0.08
     로
    -0.07
     Cach
    -0.07
     anc
    -0.07
     interrog
    -0.07
     veuillez
    -0.07
     eg
    -0.07
     MI
    -0.07
     अछि
    -0.07
    LW
    -0.07
    POSITIVE LOGITS
     ўз
    0.07
     Fitz
    0.07
    gher
    0.07
     overst
    0.07
     spider
    0.07
     vegetarian
    0.07
     thực
    0.07
    ivar
    0.07
     antif
    0.07
     Seguro
    0.07
    Activations Density 0.005%
    No Known Activations