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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65112
    Prev
    Next
    INDEX
    Explanations

    MODE

    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
    Fans
    -0.08
    भर
    -0.08
     fans
    -0.08
     subse
    -0.07
    طاق
    -0.07
    न
    -0.07
     fore
    -0.07
    новение
    -0.07
     lak
    -0.07
    ум
    -0.07
    POSITIVE LOGITS
     Dysfunction
    0.09
    vez
    0.08
     বন্ধ
    0.08
     দর
    0.08
     শেখ
    0.08
    iona
    0.08
     verein
    0.08
    zyn
    0.07
    IZ
    0.07
     Dealer
    0.07
    Activations Density 0.001%

    No Known Activations