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. 12163
    Prev
    Next
    INDEX
    Explanations

    varied topics

    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
     pás
    -0.08
    lah
    -0.08
     spé
    -0.08
    igest
    -0.07
    算盘
    -0.07
     pati
    -0.07
    LOS
    -0.07
    散
    -0.07
     Cous
    -0.07
     serm
    -0.07
    POSITIVE LOGITS
     undertake
    0.08
     donné
    0.07
     whim
    0.07
     szkol
    0.07
     אלו
    0.07
    084
    0.07
     typically
    0.07
     Leaving
    0.07
     αρ
    0.07
     anb
    0.07
    Activations Density 0.230%

    No Known Activations