© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1227
    Prev
    Next
    INDEX
    Explanations

    nested inner classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blogging
    -0.08
    nicity
    -0.08
    nic
    -0.08
     backbone
    -0.08
    (!(
    -0.07
     социаль
    -0.07
     lim
    -0.07
     �
    -0.07
     além
    -0.07
     soja
    -0.07
    POSITIVE LOGITS
    sets
    0.08
     programma
    0.08
    minen
    0.07
     Ves
    0.07
     Stewart
    0.07
     akan
    0.07
     Hoge
    0.07
     Person
    0.07
     Fence
    0.07
     tulem
    0.07
    Activations Density 0.001%

    No Known Activations