© 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. 97414
    Prev
    Next
    INDEX
    Explanations

    say "pt"

    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
    хь
    -0.09
    धानी
    -0.09
    ский
    -0.09
    ashire
    -0.09
     Civilization
    -0.09
     durum
    -0.09
    хий
    -0.08
     race
    -0.08
     three
    -0.08
    ऽ
    -0.08
    POSITIVE LOGITS
    pt
    0.16
    met
    0.13
    lines
    0.12
    metrical
    0.12
    axes
    0.12
    metrics
    0.11
    bol
    0.10
    paras
    0.10
    -lines
    0.10
    paths
    0.10
    Activations Density 0.002%

    No Known Activations