© 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. 45602
    Prev
    Next
    INDEX
    Explanations

    tempo

    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
    teur
    -0.08
    illed
    -0.08
     humid
    -0.08
    robat
    -0.07
     बैठे
    -0.07
    pflicht
    -0.07
    upy
    -0.07
    ricos
    -0.07
    idas
    -0.07
     Bios
    -0.07
    POSITIVE LOGITS
     erzielt
    0.09
     alleine
    0.08
     دوران
    0.08
     Fu
    0.08
     നേട
    0.08
     fu
    0.08
     kines
    0.07
     Tir
    0.07
     Dc
    0.07
     unk
    0.07
    Activations Density 0.004%

    No Known Activations