© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96689
    Prev
    Next
    INDEX
    Explanations

    say "the ending -anks"

    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
    ionato
    -0.10
    itim
    -0.08
    ított
    -0.08
    etako
    -0.08
     batean
    -0.08
     lute
    -0.08
     SIN
    -0.07
     SUV
    -0.07
    çiler
    -0.07
    ernes
    -0.07
    POSITIVE LOGITS
    ेंट
    0.08
     materiaal
    0.08
    materials
    0.07
     substances
    0.07
     archaeology
    0.07
    Ark
    0.07
    ેન્ટ
    0.07
    ँ
    0.07
    素材
    0.07
    ੈਂ
    0.07
    Activations Density 0.000%

    No Known Activations