© 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 EvalsExportsinterp-engineNEWAPI 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. 18476
    Prev
    Next
    INDEX
    Explanations

    say 【

    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
    ั้ง
    -0.09
    'étais
    -0.08
    'avais
    -0.08
     dg
    -0.08
    _runs
    -0.07
    	counter
    -0.07
    _side
    -0.07
    таў
    -0.07
     sandwiches
    -0.07
     Blues
    -0.07
    POSITIVE LOGITS
    Jsii
    0.09
    Its
    0.09
     उसके
    0.09
    сияи
    0.09
    0.09
    Blockchain
    0.09
    Türkmenistanyň
    0.09
    0.09
    0.09
    Firebase
    0.08
    Activations Density 0.001%
    No Known Activations