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. 90056
    Prev
    Next
    INDEX
    Explanations

    Write

    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
    exion
    -0.07
     computador
    -0.07
    .C
    -0.07
     Moore
    -0.07
     Herzog
    -0.07
    Ga
    -0.07
    нь
    -0.07
     takim
    -0.07
    湿
    -0.07
     Gir
    -0.07
    POSITIVE LOGITS
     impér
    0.09
     обязательно
    0.09
     పూర్త
    0.09
     persever
    0.08
    _ONLY
    0.08
    全过程
    0.08
     చేయ
    0.08
     పూర్తి
    0.07
     ASAP
    0.07
     Только
    0.07
    Activations Density 0.004%

    No Known Activations