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

    Neuronpedia

    Jacobian LensNEW
    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. 113732
    Prev
    Next
    INDEX
    Explanations

    abstract

    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
     Hiermee
    -0.08
    sun
    -0.08
     boats
    -0.07
     bebidas
    -0.07
    вен
    -0.07
     believed
    -0.07
     sarcast
    -0.07
    driver
    -0.07
     hereby
    -0.07
    ioneer
    -0.07
    POSITIVE LOGITS
     abstr
    0.09
     abstra
    0.09
     konkrete
    0.09
     concr
    0.09
     concreta
    0.09
     अस्प
    0.09
     abstract
    0.09
     Bureau
    0.09
     unfamiliar
    0.08
     Theorie
    0.08
    Activations Density 0.013%

    No Known Activations