© 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. 64866
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
     Inj
    -0.08
     countries
    -0.07
    wind
    -0.07
    ände
    -0.07
     conditioning
    -0.07
    ั่ง
    -0.07
     delito
    -0.07
     injury
    -0.07
     tame
    -0.07
     quasi
    -0.07
    POSITIVE LOGITS
    Sip
    0.08
    ítása
    0.08
     fermentation
    0.08
    -functions
    0.08
     Bau
    0.08
     procesu
    0.08
    -[
    0.07
     যেন
    0.07
     mythology
    0.07
     gudanar
    0.07
    Activations Density 0.001%

    No Known Activations