© 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. 71146
    Prev
    Next
    INDEX
    Explanations

    DIR

    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
    όγ
    -0.07
     சந்த
    -0.07
    碰碰
    -0.07
     पार
    -0.07
     antigen
    -0.07
     Victoria
    -0.07
     Barr
    -0.07
    -0.07
    322
    -0.07
    wegen
    -0.07
    POSITIVE LOGITS
    所在
    0.10
     Goes
    0.08
    ingroup
    0.08
     Installed
    0.07
     ();
↵
    0.07
     തന്ന
    0.07
     ?>&
    0.07
    here
    0.07
     തന്നെ
    0.07
    所属
    0.07
    Activations Density 0.001%
    No Known Activations