© 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. 29123
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     daarvoor
    -0.09
     замен
    -0.08
     firmas
    -0.08
    pụ
    -0.08
     muuta
    -0.07
    ूल
    -0.07
    套
    -0.07
    .bootstrapcdn
    -0.07
     FTP
    -0.07
     estiver
    -0.07
    POSITIVE LOGITS
    duct
    0.08
     narrated
    0.08
     Russ
    0.07
     trope
    0.07
    med
    0.07
    ummed
    0.07
    int
    0.07
    diet
    0.07
    ints
    0.07
     എഴുത
    0.07
    Activations Density 0.004%

    No Known Activations