© 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. 63210
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    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
     जिस
    -0.08
     लै
    -0.08
     풀
    -0.08
     العالي
    -0.08
     MAX
    -0.07
     Exper
    -0.07
    (MAX
    -0.07
     গোল
    -0.07
     அதிக
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    Inet
    0.08
    uary
    0.08
    반
    0.08
     shores
    0.08
    lice
    0.07
     inhabited
    0.07
     intersect
    0.07
    trap
    0.07
     apologies
    0.07
     verlassen
    0.07
    Activations Density 0.040%

    No Known Activations