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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 76084
    Prev
    Next
    INDEX
    Explanations

    bottom

    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
    hdl
    -0.09
     inhabit
    -0.08
    括
    -0.07
     tark
    -0.07
     member
    -0.07
     medlems
    -0.07
     settlement
    -0.07
     chor
    -0.07
     ta
    -0.07
     સભ
    -0.07
    POSITIVE LOGITS
    /top
    0.10
    .TOP
    0.09
     вверх
    0.09
     hardest
    0.09
    (top
    0.09
    .Flat
    0.08
    iening
    0.08
    _candidates
    0.08
    ucat
    0.08
    맛
    0.08
    Activations Density 0.011%

    No Known Activations