© 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. 11-RESID-POST-AA
    11. 110128
    Prev
    Next
    INDEX
    Explanations

    a

    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
     നേത
    -0.08
     Leaders
    -0.07
    leaders
    -0.07
    ratulations
    -0.07
    atoires
    -0.07
     shocking
    -0.07
    .reply
    -0.07
     ಪ್ರಸ
    -0.07
     رای
    -0.07
     outspoken
    -0.07
    POSITIVE LOGITS
     externo
    0.09
     Shaw
    0.09
     Himmel
    0.08
     mercados
    0.08
     externos
    0.08
     thị
    0.08
     external
    0.08
     marchés
    0.08
    _EXTERNAL
    0.08
     scenery
    0.08
    Activations Density 0.012%

    No Known Activations