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. 76307
    Prev
    Next
    INDEX
    Explanations

    thread

    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
    -0.09
     crystall
    -0.08
     આ
    -0.08
    Israel
    -0.08
    270
    -0.08
     Inc
    -0.08
     sebi
    -0.07
     ובה
    -0.07
     initi
    -0.07
    Menurut
    -0.07
    POSITIVE LOGITS
     suction
    0.08
    diam
    0.08
     reclaim
    0.08
    ەۋ
    0.08
     fre
    0.08
     Diameter
    0.08
     dah
    0.07
     nub
    0.07
    vor
    0.07
     empfind
    0.07
    Activations Density 0.001%

    No Known Activations