© 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. 54676
    Prev
    Next
    INDEX
    Explanations

    ritual

    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
    ESH
    -0.07
    usable
    -0.07
     seal
    -0.07
     colonies
    -0.07
    quarters
    -0.07
     careful
    -0.07
    -$
    -0.07
    Caught
    -0.07
    ’t
    -0.07
    ικαν
    -0.07
    POSITIVE LOGITS
     Santo
    0.10
    �
    0.08
     rituals
    0.08
     件
    0.08
     Sons
    0.08
     Mond
    0.08
    liu
    0.08
     Dew
    0.08
     praz
    0.08
     Pup
    0.08
    Activations Density 0.008%

    No Known Activations