© 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. 23-RESID-POST-AA
    11. 51776
    Prev
    Next
    INDEX
    Explanations

    سم

    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
     jornal
    -0.08
    bold
    -0.08
    ban
    -0.07
     sinabi
    -0.07
     surpass
    -0.07
     delete
    -0.07
    asos
    -0.07
     jornais
    -0.07
    .Delete
    -0.07
    bookmark
    -0.07
    POSITIVE LOGITS
    كة
    0.11
    كية
    0.10
    ندر
    0.09
    عة
    0.09
    ك
    0.09
    олет
    0.09
    ائك
    0.08
    артф
    0.08
    ائها
    0.08
    ات
    0.08
    Activations Density 0.001%

    No Known Activations