© 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. 11-RESID-POST-AA
    11. 29663
    Prev
    Next
    INDEX
    Explanations

    Calvinism

    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
     ionic
    -0.08
     chow
    -0.08
     bhu
    -0.08
     cardiac
    -0.08
     dha
    -0.08
    -divider
    -0.08
     Ionic
    -0.08
     koron
    -0.07
     paš
    -0.07
     manga
    -0.07
    POSITIVE LOGITS
    ffect
    0.08
    öss
    0.08
    作用
    0.08
    ffects
    0.08
     Stras
    0.08
    �
    0.08
     epistem
    0.08
     doctrines
    0.08
     Affirm
    0.07
    çois
    0.07
    Activations Density 0.013%

    No Known Activations