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. 90236
    Prev
    Next
    INDEX
    Explanations

    Amazon

    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
    dy
    -0.10
    auan
    -0.09
     treten
    -0.08
     dy
    -0.08
     Freib
    -0.08
     Bog
    -0.08
     Trink
    -0.07
    ATURE
    -0.07
    ाचार
    -0.07
     Singing
    -0.07
    POSITIVE LOGITS
    .com
    0.10
     continually
    0.08
     Kindle
    0.08
    .amazon
    0.08
     mog
    0.08
    Basics
    0.08
    bic
    0.08
    -funded
    0.08
    .com's
    0.07
    compr
    0.07
    Activations Density 0.005%

    No Known Activations