© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44634
    Prev
    Next
    INDEX
    Explanations

    Live performances

    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
    _gradient
    -0.09
     gradient
    -0.09
    负责人
    -0.08
    _grad
    -0.08
    担当
    -0.08
     masculine
    -0.08
     gradients
    -0.08
    owners
    -0.08
    ograd
    -0.08
    oczes
    -0.08
    POSITIVE LOGITS
     recordings
    0.16
     filmed
    0.15
    Recorded
    0.14
    Recording
    0.14
    録
    0.13
     Recorded
    0.13
     recording
    0.13
     Recording
    0.12
    录像
    0.12
     footage
    0.12
    Activations Density 0.044%

    No Known Activations