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. 45663
    Prev
    Next
    INDEX
    Explanations

    communication

    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
    -mounted
    -0.08
    -wide
    -0.08
     fragments
    -0.07
     features
    -0.07
     특징
    -0.07
    ockey
    -0.07
     altitude
    -0.07
    -safe
    -0.07
    ificant
    -0.07
    issippi
    -0.07
    POSITIVE LOGITS
    反馈
    0.10
     sukses
    0.10
    feedback
    0.09
    sender
    0.09
     pozw
    0.09
     Sender
    0.09
     回复
    0.09
     ontv
    0.09
     sender
    0.08
     destinat
    0.08
    Activations Density 0.006%

    No Known Activations