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. 130462
    Prev
    Next
    INDEX
    Explanations

    之间

    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
     cand
    -0.08
     contours
    -0.07
    ARC
    -0.07
     effektiv
    -0.07
    (Rel
    -0.07
     MPC
    -0.07
    ద్ద
    -0.07
     comprend
    -0.07
     تحقق
    -0.07
    itative
    -0.07
    POSITIVE LOGITS
     sticking
    0.09
     numbered
    0.08
     elkaar
    0.08
    rdquo
    0.08
     birbir
    0.08
     vone
    0.08
     newline
    0.08
     Каж
    0.08
    ანი
    0.08
     रक्षा
    0.08
    Activations Density 0.001%

    No Known Activations