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. 102907
    Prev
    Next
    INDEX
    Explanations

    wh

    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
     enfermedad
    -0.07
    这个
    -0.07
     maladie
    -0.07
    机场
    -0.07
     Reise
    -0.07
     notoriously
    -0.07
    斯
    -0.07
     PMS
    -0.07
    _PRO
    -0.07
    按
    -0.07
    POSITIVE LOGITS
     сю
    0.09
    CAE
    0.09
    WY
    0.08
     βα
    0.08
     parity
    0.08
    _virtual
    0.08
    mw
    0.08
     benar
    0.08
     bantuan
    0.08
     оди
    0.08
    Activations Density 0.000%

    No Known Activations