© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 17990
    Prev
    Next
    INDEX
    Explanations

    prompt

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     another
    -0.10
     when
    -0.09
     over
    -0.09
    ('/')
    -0.08
     etmek
    -0.08
    另
    -0.08
     similar
    -0.08
     considerar
    -0.08
     again
    -0.08
     counterpart
    -0.08
    POSITIVE LOGITS
     Sentence
    0.12
    ：[
    0.11
        ↵↵
    0.11
    :first
    0.11
    >[
    0.11
     Clause
    0.11
    	X
    0.10
        ↵    ↵    ↵    ↵
    0.10
    ：【
    0.10
    :[↵
    0.10
    Activations Density 0.001%

    No Known Activations