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. 98310
    Prev
    Next
    INDEX
    Explanations

    also

    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
    Hello
    -0.08
     Hello
    -0.08
    پ
    -0.07
    لل
    -0.07
    Living
    -0.07
     Aud
    -0.07
     loin
    -0.07
    san
    -0.07
     Carnival
    -0.07
    Virginia
    -0.07
    POSITIVE LOGITS
     want
    0.11
    want
    0.10
     можем
    0.09
     తెలుస
    0.09
     দেখি
    0.09
    ’ll
    0.08
     છીએ
    0.08
     будем
    0.08
     চাই
    0.08
     করছি
    0.08
    Activations Density 0.019%

    No Known Activations