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. 11589
    Prev
    Next
    INDEX
    Explanations

    Colon

    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
    hoof
    -0.09
    htable
    -0.08
    flight
    -0.08
     подход
    -0.08
     распис
    -0.08
     изуч
    -0.08
    ਾਹ
    -0.08
     hool
    -0.08
     wunder
    -0.08
     jouw
    -0.07
    POSITIVE LOGITS
     acknowled
    0.09
     قل
    0.08
     acknowledges
    0.08
     अर
    0.08
     coherence
    0.07
    chip
    0.07
     chip
    0.07
     опять
    0.07
     acknowledge
    0.07
     기타
    0.07
    Activations Density 0.030%

    No Known Activations