© 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. 71338
    Prev
    Next
    INDEX
    Explanations

    extends

    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
    else
    -0.08
     hoef
    -0.08
     enhancements
    -0.07
    ksel
    -0.07
     RH
    -0.07
    nde
    -0.07
     россий
    -0.07
     navn
    -0.07
     gaat
    -0.07
     сек
    -0.07
    POSITIVE LOGITS
     IDisposable
    0.08
     laptops
    0.08
     Loft
    0.08
     Candidates
    0.08
     Retina
    0.07
    കാര്യ
    0.07
    kušen
    0.07
     Laval
    0.07
    Lav
    0.07
     Lou
    0.07
    Activations Density 0.000%

    No Known Activations