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. 12971
    Prev
    Next
    INDEX
    Explanations

    programming errors

    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
     mindfulness
    -0.08
    ='"
    -0.07
    铭
    -0.07
    ardless
    -0.07
     constraints
    -0.07
     exemplary
    -0.07
    =l
    -0.07
     generous
    -0.07
     altru
    -0.07
     intra
    -0.07
    POSITIVE LOGITS
     неправ
    0.09
     tulem
    0.09
     емес
    0.09
    /string
    0.09
     ahubwo
    0.09
     sondern
    0.09
    boolean
    0.08
     terlalu
    0.08
     incorrectly
    0.08
     түгел
    0.08
    Activations Density 0.017%

    No Known Activations