© 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. 23-RESID-POST-AA
    11. 48085
    Prev
    Next
    INDEX
    Explanations

    sob

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     junction
    -0.08
     quitt
    -0.08
    -est
    -0.07
     out
    -0.07
     Jú
    -0.07
     copying
    -0.07
     황
    -0.07
    Bag
    -0.07
     EST
    -0.07
     hesab
    -0.07
    POSITIVE LOGITS
    лайн
    0.08
    linen
    0.08
    usize
    0.08
     لاين
    0.08
    טע
    0.08
    orries
    0.08
    ליין
    0.07
    买马
    0.07
    IDE
    0.07
    אני
    0.07
    Activations Density 0.001%

    No Known Activations