© 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. 551
    Prev
    Next
    INDEX
    Explanations

    decreased

    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
    rology
    -0.08
    fortunate
    -0.08
     memper
    -0.08
    就在
    -0.07
     доказ
    -0.07
     изменить
    -0.07
     Clair
    -0.07
     внес
    -0.07
     refundable
    -0.07
     настоя
    -0.07
    POSITIVE LOGITS
     anxiety
    0.14
     ansiedad
    0.13
     Anxiety
    0.13
     ansiedade
    0.12
     तनाव
    0.11
     anxious
    0.11
    疲
    0.11
     fears
    0.11
    炎
    0.10
     воспал
    0.10
    Activations Density 0.015%

    No Known Activations