© 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. 999
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Premium
    -0.07
    .At
    -0.07
     empe
    -0.07
    .protobuf
    -0.07
    책
    -0.07
     cpu
    -0.07
     프로
    -0.07
     Micros
    -0.07
     માર્ગ
    -0.07
     શું
    -0.07
    POSITIVE LOGITS
     likewise
    0.09
     Edith
    0.09
    之
    0.08
     Shirley
    0.08
     которому
    0.08
     Abbas
    0.08
    pz
    0.08
    icale
    0.07
    irho
    0.07
    ור
    0.07
    Activations Density 0.119%

    No Known Activations