© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99763
    Prev
    Next
    INDEX
    Explanations

    Sending information

    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
     अब
    -0.09
     offenbar
    -0.08
     implying
    -0.08
     offensichtlich
    -0.08
     passieren
    -0.08
    =query
    -0.08
     छोट
    -0.08
     priori
    -0.08
     pervasive
    -0.08
     wpis
    -0.07
    POSITIVE LOGITS
     rud
    0.08
    ociation
    0.07
    óleo
    0.07
     Länder
    0.07
    enschutz
    0.07
     Accounts
    0.07
     civ
    0.07
     conoz
    0.07
    oleg
    0.07
     selectively
    0.07
    Activations Density 0.053%

    No Known Activations