© 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. 108791
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Crane
    -0.09
     Colt
    -0.07
     nonetheless
    -0.07
     whims
    -0.07
     NSA
    -0.07
    ']->
    -0.07
    iddi
    -0.07
    Compiled
    -0.07
     Subsid
    -0.07
     segue
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.09
     гг
    0.08
     alike
    0.08
     dư
    0.08
     килом
    0.08
     മണിക്ക
    0.08
     ഇര
    0.08
     resting
    0.08
    ൾ
    0.08
     זייער
    0.08
    Activations Density 0.046%

    No Known Activations