© 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. 23-RESID-POST-AA
    11. 49236
    Prev
    Next
    INDEX
    Explanations

    say the ending -orn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gav
    -0.08
     мн
    -0.07
     taane
    -0.07
     हस्त
    -0.07
    -0.07
     μια
    -0.07
    ENSOR
    -0.07
    .Op
    -0.07
     переп
    -0.07
     gada
    -0.07
    POSITIVE LOGITS
    ębior
    0.08
    CDF
    0.08
     ಭಾಗ
    0.08
    icz
    0.08
    frm
    0.07
    niu
    0.07
    cdf
    0.07
    Gem
    0.07
     adopté
    0.07
    cem
    0.07
    Activations Density 0.000%

    No Known Activations