© 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. 15-RESID-POST-AA
    11. 16561
    Prev
    Next
    INDEX
    Explanations

    elephant

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indie
    -0.08
     publicada
    -0.08
     게시
    -0.08
    posting
    -0.08
     Ke
    -0.08
     rápida
    -0.08
     પ્રકાશ
    -0.08
     burnout
    -0.08
     Taifa
    -0.08
     steels
    -0.08
    POSITIVE LOGITS
     elephants
    0.14
    phants
    0.11
     elephant
    0.10
     Elephant
    0.10
     Ivory
    0.09
     gigantic
    0.09
    สัต
    0.09
     afric
    0.08
     discap
    0.08
     tactile
    0.08
    Activations Density 0.008%

    No Known Activations