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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5883
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ibbli
    -0.09
    éd
    -0.08
     Iber
    -0.08
    estead
    -0.08
     йез
    -0.08
    umist
    -0.08
    -win
    -0.08
    ожал
    -0.08
    �ლი
    -0.08
    'wi
    -0.08
    POSITIVE LOGITS
     Cro
    0.16
     cro
    0.13
     Cr
    0.13
     crore
    0.12
     lac
    0.12
     rs
    0.12
     kms
    0.12
     Lac
    0.11
     cr
    0.11
    (cr
    0.11
    Activations Density 0.050%

    No Known Activations