© 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. 18169
    Prev
    Next
    INDEX
    Explanations

    at

    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
     એવી
    -0.10
     ausgesprochen
    -0.08
     ऐसी
    -0.08
     financeiras
    -0.08
    一句
    -0.08
     nadat
    -0.08
    よう
    -0.08
     someday
    -0.08
    ，使
    -0.08
     waarna
    -0.08
    POSITIVE LOGITS
     candidates
    0.12
     relevant
    0.12
     kandid
    0.11
     relevante
    0.11
    andidates
    0.11
    Candidates
    0.10
    _candidates
    0.10
     candidate
    0.10
    Relevant
    0.10
     후보
    0.10
    Activations Density 0.018%

    No Known Activations