© 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. 110223
    Prev
    Next
    INDEX
    Explanations

    activist

    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
    .Preference
    -0.09
    -unused
    -0.08
    uisse
    -0.08
     implanted
    -0.08
    ricula
    -0.08
     Hrvats
    -0.08
    �s
    -0.08
    _nullable
    -0.08
     filial
    -0.08
     Toshiba
    -0.07
    POSITIVE LOGITS
     вокруг
    0.09
    amping
    0.08
    Countdown
    0.08
     potency
    0.08
    推动
    0.08
     messaging
    0.08
     activism
    0.07
     redness
    0.07
     Ebola
    0.07
    ,target
    0.07
    Activations Density 0.039%

    No Known Activations