© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51962
    Prev
    Next
    INDEX
    Explanations

    пос

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    സ്ക
    -0.08
     וצ
    -0.07
    ESC
    -0.07
    ട
    -0.07
     Jewel
    -0.07
     ja
    -0.07
     anecdotes
    -0.07
    સ્ક
    -0.07
     distinctions
    -0.07
    स्क
    -0.07
    POSITIVE LOGITS
    лал
    0.08
    одейств
    0.08
    пе
    0.08
    _IM
    0.08
    реди
    0.08
    0.08
    .IM
    0.08
    ברים
    0.08
    reck
    0.08
    сор
    0.08
    Activations Density 0.000%
    No Known Activations