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. 27270
    Prev
    Next
    INDEX
    Explanations

    Forbes

    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
     SP
    -0.08
    室
    -0.08
    Slip
    -0.08
     vaginal
    -0.08
     Mm
    -0.07
     VK
    -0.07
     vacaciones
    -0.07
    取り
    -0.07
     AVC
    -0.07
     Vk
    -0.07
    POSITIVE LOGITS
    榜
    0.09
    -family
    0.08
     Ya
    0.08
     handful
    0.08
     Teen
    0.08
    frog
    0.08
     influencer
    0.08
    旗下
    0.08
    大陆
    0.08
     beef
    0.08
    Activations Density 0.005%

    No Known Activations