© 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. 23-RESID-POST-AA
    11. 49809
    Prev
    Next
    INDEX
    Explanations

    concl

    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
    iolet
    -0.10
    ulare
    -0.09
    jaman
    -0.09
     llevado
    -0.08
    licenses
    -0.08
    cri
    -0.08
    arlas
    -0.08
     влад
    -0.08
    орол
    -0.08
    اريات
    -0.08
    POSITIVE LOGITS
    േ
    0.08
     Curtis
    0.08
     απο
    0.07
    _cursor
    0.07
     darauf
    0.07
     abundance
    0.07
     Onde
    0.07
    ാം
    0.07
    (()
    0.07
     עליו
    0.07
    Activations Density 0.000%

    No Known Activations