© 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. 52299
    Prev
    Next
    INDEX
    Explanations

    cubes

    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
    Negative Logits
     כנ
    -0.08
    endu
    -0.08
     vergadering
    -0.08
     patr
    -0.08
    ayd
    -0.08
     pensamentos
    -0.08
     Oster
    -0.08
     inaug
    -0.08
     tany
    -0.07
     مدیر
    -0.07
    POSITIVE LOGITS
    27
    0.15
    125
    0.13
    216
    0.12
    343
    0.12
     куб
    0.11
    -c
    0.10
    _cb
    0.10
    172
    0.10
    729
    0.10
    274
    0.10
    Activations Density 0.076%

    No Known Activations