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. 74532
    Prev
    Next
    INDEX
    Explanations

    OCR text fragments

    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
     freiwill
    -0.10
     Dirty
    -0.09
     vrijwill
    -0.09
     terug
    -0.09
     напрямую
    -0.08
     добров
    -0.08
     фен
    -0.08
    _dirty
    -0.08
    -imi
    -0.08
     hyv
    -0.08
    POSITIVE LOGITS
    릴
    0.08
    器
    0.08
    wag
    0.07
    choose
    0.07
    ړ
    0.07
    TRA
    0.07
    ρών
    0.07
    رد
    0.07
     crus
    0.07
     deducted
    0.07
    Activations Density 0.065%

    No Known Activations