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. 60777
    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
    @author
    -0.08
    senha
    -0.08
     pseudo
    -0.08
     Matthew
    -0.07
     앞
    -0.07
    లా
    -0.07
     yakho
    -0.07
     댓글
    -0.07
    댓글
    -0.07
    Parametros
    -0.07
    POSITIVE LOGITS
     mand
    0.08
     erat
    0.08
     rū
    0.08
     ā
    0.08
     r
    0.07
     Thema
    0.07
    0.07
     �
    0.07
     comun
    0.07
     ehd
    0.07
    Activations Density 0.009%

    No Known Activations