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. 98440
    Prev
    Next
    INDEX
    Explanations

    junior

    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
    .gs
    -0.08
     betal
    -0.08
    ��
    -0.07
    tru
    -0.07
    овать
    -0.07
     trat
    -0.07
    רא
    -0.07
    ующий
    -0.07
     naissance
    -0.07
    ुअ
    -0.07
    POSITIVE LOGITS
    🏼
    0.08
    _indicator
    0.08
     Jerome
    0.08
    精神
    0.07
     Beng
    0.07
    CB
    0.07
     Lis
    0.07
     amend
    0.07
    ────────────────
    0.07
     Rabbi
    0.07
    Activations Density 0.005%

    No Known Activations