© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 51101
    Prev
    Next
    INDEX
    Explanations

    hard

    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
     lastig
    -0.10
    ेप
    -0.09
    ोटी
    -0.08
    heim
    -0.08
     espí
    -0.08
     Twilight
    -0.08
     tod
    -0.08
     jelent
    -0.08
     Ember
    -0.08
    Dance
    -0.08
    POSITIVE LOGITS
     edges
    0.09
    .edge
    0.08
     appropri
    0.08
     lining
    0.08
    .edges
    0.08
     стоят
    0.08
     edge
    0.08
     લેવ
    0.08
    inery
    0.07
     power
    0.07
    Activations Density 0.004%

    No Known Activations