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. 29827
    Prev
    Next
    INDEX
    Explanations

    change and replacement

    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
     hypothetical
    -0.08
     pak
    -0.08
     Mod
    -0.08
     modalités
    -0.07
     modalità
    -0.07
     dinám
    -0.07
     Sik
    -0.07
     hipot
    -0.07
    )을
    -0.07
    인
    -0.07
    POSITIVE LOGITS
     merely
    0.12
     superficial
    0.11
     superfic
    0.11
     mere
    0.10
     مجرد
    0.09
     veneer
    0.09
     तथ्य
    0.09
     rote
    0.09
     passt
    0.09
    mere
    0.08
    Activations Density 0.121%

    No Known Activations