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. 119252
    Prev
    Next
    INDEX
    Explanations

    off-chain

    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
     bezit
    -0.08
    岗位
    -0.08
    ifficulty
    -0.08
    'esp
    -0.08
    ’esp
    -0.08
    _VAR
    -0.08
     forvent
    -0.08
    <Role
    -0.08
    <size
    -0.07
     sabotage
    -0.07
    POSITIVE LOGITS
     сделки
    0.10
     stattfinden
    0.10
     происход
    0.09
     plaatsvinden
    0.09
     transactions
    0.09
     transaksi
    0.09
     общения
    0.09
    .transactions
    0.08
     privados
    0.08
     interactions
    0.08
    Activations Density 0.032%

    No Known Activations