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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 79031
    Prev
    Next
    INDEX
    Explanations

    Chechnya

    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
     gase
    -0.09
    ศัพท์
    -0.09
     chocolates
    -0.09
    Chocolate
    -0.08
     dashed
    -0.08
    &i
    -0.08
    ว
    -0.08
    이에
    -0.08
     refrigerators
    -0.08
    :&
    -0.08
    POSITIVE LOGITS
     hairs
    0.08
     Voices
    0.08
     krv
    0.08
    _STAGE
    0.08
     elite
    0.08
     fiercely
    0.07
     lutter
    0.07
    规模
    0.07
     gait
    0.07
     tribes
    0.07
    Activations Density 0.002%

    No Known Activations