© 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. 11-RESID-POST-AA
    11. 70262
    Prev
    Next
    INDEX
    Explanations

    nice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    扫描
    -0.08
    tpl
    -0.08
     cuffs
    -0.08
     scanned
    -0.07
     ured
    -0.07
    endr
    -0.07
     misconceptions
    -0.07
    签到
    -0.07
    ruk
    -0.07
     commodo
    -0.07
    POSITIVE LOGITS
     sedent
    0.09
    (priority
    0.09
    =subprocess
    0.09
     مستوى
    0.08
     Whisper
    0.08
     priorities
    0.08
    เต็ม
    0.08
     MPC
    0.08
     whisper
    0.08
     شهری
    0.08
    Activations Density 0.005%

    No Known Activations