© 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. 26235
    Prev
    Next
    INDEX
    Explanations

    red, infrared

    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
    ाकार
    -0.08
     lâ
    -0.08
     linen
    -0.08
     legendary
    -0.08
     जिसके
    -0.08
     fal
    -0.08
     proverbial
    -0.08
     sart
    -0.08
     hydraulic
    -0.08
     glazen
    -0.08
    POSITIVE LOGITS
     burner
    0.08
     ور
    0.08
     tones
    0.07
     Facility
    0.07
     facility
    0.07
     primordial
    0.07
     considerations
    0.07
    415
    0.07
    νη
    0.07
     prim
    0.07
    Activations Density 0.004%

    No Known Activations