© 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. 29609
    Prev
    Next
    INDEX
    Explanations

    redemption

    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
    lego
    -0.08
     бю
    -0.07
     Wow
    -0.07
     gen
    -0.07
     ozone
    -0.07
     pard
    -0.07
     oficina
    -0.07
     comput
    -0.07
     конкур
    -0.07
     oud
    -0.07
    POSITIVE LOGITS
     보기
    0.09
    places
    0.08
     Ladder
    0.08
     ladder
    0.08
    ांकन
    0.08
    psilon
    0.08
     чего
    0.07
     കൊണ്ട
    0.07
     마련
    0.07
    .cg
    0.07
    Activations Density 0.003%

    No Known Activations