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. 58103
    Prev
    Next
    INDEX
    Explanations

    also/as

    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
     potrz
    -0.09
     elk
    -0.08
     tard
    -0.08
     memakai
    -0.08
    हरु
    -0.07
    ILY
    -0.07
     haka
    -0.07
    ೆಯಾಗ
    -0.07
    Anno
    -0.07
    స్
    -0.07
    POSITIVE LOGITS
     на
    0.08
     scrolling
    0.07
    ρισ
    0.07
     оцен
    0.07
    ко
    0.07
    _WE
    0.07
     perfil
    0.07
    ключ
    0.07
    кір
    0.07
    .mix
    0.07
    Activations Density 0.013%

    No Known Activations