Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43922
    Prev
    Next
    INDEX
    Explanations

    prompt

    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
     rendimento
    -0.08
    �
    -0.08
    609
    -0.08
     thresholds
    -0.08
    ancy
    -0.08
     puzz
    -0.08
    ব্য
    -0.07
     зы
    -0.07
    quo
    -0.07
    'eb
    -0.07
    POSITIVE LOGITS
     einschließlich
    0.08
     التفاصيل
    0.08
     С
    0.08
     inclusief
    0.08
     ਅ
    0.08
     Relay
    0.07
     Compart
    0.07
    praken
    0.07
     preferably
    0.07
     REL
    0.07
    Activations Density 0.010%

    No Known Activations