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. 113939
    Prev
    Next
    INDEX
    Explanations

    detective

    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
    mi
    -0.08
     znam
    -0.07
     frequencies
    -0.07
     emphasis
    -0.07
    ଛ
    -0.07
    -defined
    -0.07
    over
    -0.07
    तः
    -0.06
    error
    -0.06
     periodic
    -0.06
    POSITIVE LOGITS
    Witness
    0.08
     balm
    0.08
     જુ
    0.08
     getaway
    0.08
     intval
    0.08
     wad
    0.08
     guy
    0.08
     Counsel
    0.08
     韦
    0.07
     Ville
    0.07
    Activations Density 0.004%

    No Known Activations