© 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. 48248
    Prev
    Next
    INDEX
    Explanations

    say "number 5"

    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
    786
    -0.09
    urations
    -0.09
    mnopqrst
    -0.09
     башқ
    -0.08
    585
    -0.08
    ’exercice
    -0.08
    ्काल
    -0.08
    ابط
    -0.08
     mmol
    -0.08
     mantel
    -0.08
    POSITIVE LOGITS
    ਅ
    0.08
    ਤ
    0.07
    Strike
    0.07
    .domain
    0.07
    Modal
    0.07
    Leaks
    0.07
    modal
    0.07
    config
    0.07
    ਫ
    0.07
    const
    0.07
    Activations Density 0.000%

    No Known Activations