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. 117642
    Prev
    Next
    INDEX
    Explanations

    track

    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
     biblical
    -0.08
     scripture
    -0.08
     candidature
    -0.08
     wholesale
    -0.08
    (E
    -0.07
     ethers
    -0.07
    emende
    -0.07
    ägen
    -0.07
    (hero
    -0.07
     Jasper
    -0.07
    POSITIVE LOGITS
     circumference
    0.09
    圈
    0.09
    .CL
    0.09
    .Circle
    0.09
    .circle
    0.08
     contours
    0.08
    puan
    0.08
    上的
    0.08
     oval
    0.08
    ulat
    0.08
    Activations Density 0.005%

    No Known Activations