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. 41996
    Prev
    Next
    INDEX
    Explanations

    ::

    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
    -faire
    -0.08
    Pr
    -0.08
     प्रस
    -0.08
    *******
    -0.08
    슬
    -0.07
    sla
    -0.07
     호텔
    -0.07
     कानून
    -0.07
     pragma
    -0.07
    62
    -0.07
    POSITIVE LOGITS
     nomin
    0.07
     ö
    0.07
     сына
    0.07
    Discover
    0.07
     brak
    0.07
     Discover
    0.07
     മുമ്പ
    0.07
    famil
    0.07
    痛
    0.07
     interm
    0.07
    Activations Density 0.000%

    No Known Activations