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. 364
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    бу
    -0.09
     improv
    -0.08
    {
    ↵//
    -0.08
    -tour
    -0.08
    (btn
    -0.07
    .btn
    -0.07
     Btn
    -0.07
    Оч
    -0.07
    따
    -0.07
    「あ
    -0.07
    POSITIVE LOGITS
    providername
    0.08
     volv
    0.07
    াইন
    0.07
    vsem
    0.07
    ρού
    0.07
    assium
    0.07
    ared
    0.07
    _provider
    0.07
    gaven
    0.07
    ro
    0.07
    Activations Density 0.024%

    No Known Activations