© 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. 48035
    Prev
    Next
    INDEX
    Explanations

    say "on"

    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
    issingen
    -0.10
    isku
    -0.09
    isumik
    -0.09
     produktu
    -0.08
    имен
    -0.08
    ippaa
    -0.08
     мект
    -0.08
    issamik
    -0.08
    -министр
    -0.08
    issamut
    -0.08
    POSITIVE LOGITS
    b
    0.12
    bulas
    0.10
    cr
    0.10
    far
    0.10
    'er
    0.09
    cro
    0.09
    ón
    0.08
    bul
    0.08
    .into
    0.08
    ’er
    0.08
    Activations Density 0.001%

    No Known Activations