© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5555
    Prev
    Next
    INDEX
    Explanations

    Z

    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
    Mand
    -0.09
    wow
    -0.09
     أخ
    -0.09
     پہن
    -0.09
     جگ
    -0.08
     viva
    -0.08
     ete
    -0.08
    mand
    -0.08
    เทศ
    -0.08
    prijzen
    -0.08
    POSITIVE LOGITS
    53
    0.09
    72
    0.08
     propositions
    0.08
    490
    0.08
    180
    0.08
    510
    0.08
    270
    0.07
    723
    0.07
     प्रो
    0.07
    73
    0.07
    Activations Density 0.000%

    No Known Activations