© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 215
    Prev
    Next
    INDEX
    Explanations

    electricity

    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
     préd
    -0.08
    .manual
    -0.07
    pred
    -0.07
     handic
    -0.07
     adına
    -0.07
     prednisone
    -0.07
     Sinn
    -0.07
     sandstone
    -0.07
    'É
    -0.07
    exp
    -0.07
    POSITIVE LOGITS
     applied
    0.10
     Applied
    0.10
    Applied
    0.09
     الجلد
    0.08
    -dismiss
    0.08
     dolphins
    0.08
    linge
    0.07
     हमला
    0.07
    .skin
    0.07
     liger
    0.07
    Activations Density 0.003%

    No Known Activations