© 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. 19-RESID-POST-AA
    11. 102980
    Prev
    Next
    INDEX
    Explanations

    Mathematical equations

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JL
    -0.07
     myth
    -0.07
    -friendly
    -0.07
    odus
    -0.07
    cial
    -0.07
     опыт
    -0.07
    ifica
    -0.07
    cio
    -0.07
    uitary
    -0.07
    ial
    -0.07
    POSITIVE LOGITS
    туруш
    0.09
    	use
    0.09
     use
    0.08
    ায়ে
    0.08
    )(((
    0.08
     toezicht
    0.08
    ահար
    0.08
     ರಾಜ್ಯ
    0.08
     өм
    0.08
    ２０１
    0.08
    Activations Density 0.090%

    No Known Activations