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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 54047
    Prev
    Next
    INDEX
    Explanations

    Mathematics

    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
    .area
    -0.09
    _DIFF
    -0.08
     Area
    -0.08
     نتیجه
    -0.08
     �
    -0.08
     teine
    -0.07
     മലയാള
    -0.07
    avored
    -0.07
    ാസ
    -0.07
     ചെന്ന
    -0.07
    POSITIVE LOGITS
    ంగా
    0.08
     rather
    0.08
    ವಾಗಿ
    0.08
     anymore
    0.07
     Shah
    0.07
     sondern
    0.07
    ੀਆਂ
    0.07
    LEnc
    0.07
     jug
    0.07
    。如
    0.07
    Activations Density 0.104%

    No Known Activations