© 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. 54896
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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
    موعة
    -0.07
     mail
    -0.07
     poucos
    -0.07
     nossos
    -0.07
     unusual
    -0.07
     autoridades
    -0.07
     hok
    -0.07
    ）、
    -0.07
     maquinaria
    -0.07
     nos
    -0.07
    POSITIVE LOGITS
    sha
    0.07
    Block
    0.07
     fres
    0.07
     অপেক্ষ
    0.07
     Gip
    0.07
     FMI
    0.07
    ."
    0.07
     rendering
    0.07
    (Block
    0.07
     Crawford
    0.07
    Activations Density 0.044%

    No Known Activations