Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53976
    Prev
    Next
    INDEX
    Explanations

    Suffixes

    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
    .Ans
    -0.09
     القضية
    -0.08
    .note
    -0.08
     عَل
    -0.07
    .angular
    -0.07
     nove
    -0.07
     Bestellung
    -0.07
     andern
    -0.07
     deen
    -0.07
     Outs
    -0.07
    POSITIVE LOGITS
     हूँ
    0.09
     han
    0.08
     responsable
    0.08
    bot
    0.08
    annya
    0.07
     සිට
    0.07
     છું
    0.07
     છો
    0.07
    lebnis
    0.07
    Cf
    0.07
    Activations Density 0.172%

    No Known Activations