© 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. 11-RESID-POST-AA
    6. 77921
    Prev
    Next
    INDEX
    Explanations

    opt

    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
     Tod
    -0.08
    Maps
    -0.07
    ない
    -0.07
     chiefs
    -0.07
    engers
    -0.07
    Mak
    -0.07
     squads
    -0.07
     Rais
    -0.07
     Orchestra
    -0.07
    Millan
    -0.07
    POSITIVE LOGITS
     YES
    0.09
    研
    0.08
     behalf
    0.08
     funnel
    0.07
     lax
    0.07
    etric
    0.07
    不过
    0.07
    ане
    0.07
     прем
    0.07
     citrate
    0.07
    Activations Density 0.005%

    No Known Activations