© 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. 110922
    Prev
    Next
    INDEX
    Explanations

    flag

    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
     vanish
    -0.08
     billed
    -0.07
     auditory
    -0.07
     TSR
    -0.07
     enlarged
    -0.07
    提示
    -0.07
    inti
    -0.07
    リーズ
    -0.07
    כת
    -0.07
     Payments
    -0.07
    POSITIVE LOGITS
    چه
    0.09
     Candida
    0.08
    aux
    0.08
     सैन
    0.08
     tric
    0.08
    Ocean
    0.08
     Leuk
    0.07
     waving
    0.07
    Marine
    0.07
     precar
    0.07
    Activations Density 0.004%

    No Known Activations