© 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. 18274
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    Not in Any Lists

    No Comments

    Negative Logits
     microscopic
    -0.09
     mathematics
    -0.09
     eniyan
    -0.09
     människor
    -0.09
     watu
    -0.09
     मानिस
    -0.08
    ებელ
    -0.08
     tilma
    -0.08
    ொரு
    -0.08
     microfiber
    -0.08
    POSITIVE LOGITS
    credential
    0.09
     each
    0.08
    ub
    0.08
    esters
    0.08
     fleets
    0.08
    0.08
    UB
    0.08
    s
    0.08
    ğiz
    0.08
    entre
    0.08
    Activations Density 0.004%
    No Known Activations