© 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. 23-RESID-POST-AA
    11. 51938
    Prev
    Next
    INDEX
    Explanations

    as

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    semble
    -0.10
     Perhaps
    -0.09
    umd
    -0.08
     unicode
    -0.08
     provided
    -0.08
     навед
    -0.08
     caliente
    -0.08
     pensei
    -0.07
     avond
    -0.07
     nav
    -0.07
    POSITIVE LOGITS
    son
    0.15
    sons
    0.10
    sonian
    0.10
    SON
    0.09
    tom
    0.08
    sono
    0.08
    pecific
    0.08
    ss
    0.08
    們
    0.08
    ales
    0.08
    Activations Density 0.003%

    No Known Activations