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. 59016
    Prev
    Next
    INDEX
    Explanations

    heritage

    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
     iv
    -0.08
     predictable
    -0.08
     zat
    -0.08
     fib
    -0.08
     প্রব
    -0.07
     нак
    -0.07
     pegar
    -0.07
     благ
    -0.07
     steep
    -0.07
    _iv
    -0.07
    POSITIVE LOGITS
     banget
    0.08
    isted
    0.08
    yk
    0.08
    -listed
    0.08
    /business
    0.07
     heg
    0.07
    潮
    0.07
     pany
    0.07
     ASE
    0.07
    _Node
    0.07
    Activations Density 0.003%

    No Known Activations