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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 106354
    Prev
    Next
    INDEX
    Explanations

    -

    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
     permanecer
    -0.08
     nähdä
    -0.07
     sufrir
    -0.07
     ev
    -0.07
     होने
    -0.07
    FS
    -0.07
    ள்வ
    -0.07
    ASURE
    -0.07
    Hg
    -0.07
     parody
    -0.07
    POSITIVE LOGITS
     Traf
    0.08
    ssd
    0.08
     Routed
    0.08
     Wellington
    0.07
    ورة
    0.07
     Ubuntu
    0.07
     Kontext
    0.07
     Gour
    0.07
     Česk
    0.07
    ිත
    0.07
    Activations Density 0.001%

    No Known Activations