© 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. 23-RESID-POST-AA
    11. 51779
    Prev
    Next
    INDEX
    Explanations

    Chinese punctuation

    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
     fry
    -0.08
    (u
    -0.08
    *u
    -0.08
     squeez
    -0.08
     sampai
    -0.08
     mashed
    -0.07
    Oliver
    -0.07
    (user
    -0.07
     isle
    -0.07
    (ts
    -0.07
    POSITIVE LOGITS
    十大
    0.10
    Dep
    0.08
     oxidative
    0.08
     Loki
    0.08
     Dep
    0.08
     Mao
    0.08
     newer
    0.08
    利来
    0.08
     azul
    0.08
     manga
    0.08
    Activations Density 0.001%

    No Known Activations