Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53209
    Prev
    Next
    INDEX
    Explanations

    enter

    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
     indicates
    -0.08
     rods
    -0.08
    Slim
    -0.07
    特别
    -0.07
    Living
    -0.07
    Kort
    -0.07
    288
    -0.07
    除了
    -0.07
     draait
    -0.07
     brom
    -0.07
    POSITIVE LOGITS
    onom
    0.09
    lden
    0.08
    .Pattern
    0.08
     DEN
    0.08
     Αυ
    0.07
    amble
    0.07
     Mid
    0.07
    deprecated
    0.07
     onn
    0.07
     المعرفة
    0.07
    Activations Density 0.001%

    No Known Activations