© 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. 7-RESID-POST-AA
    11. 1135
    Prev
    Next
    INDEX
    Explanations

    plus sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buried
    -0.07
    ட்டி
    -0.07
    ਜ਼
    -0.07
    /general
    -0.07
    Tas
    -0.07
    etag
    -0.07
     cập
    -0.07
     fantástico
    -0.07
     motives
    -0.07
     lob
    -0.07
    POSITIVE LOGITS
     produces
    0.09
     Kultur
    0.09
     expensive
    0.09
     Upt
    0.08
     stiff
    0.08
     Margar
    0.08
     Pico
    0.08
     Met
    0.08
     vr
    0.08
     Linen
    0.08
    Activations Density 0.008%

    No Known Activations