© 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. 6303
    Prev
    Next
    INDEX
    Explanations

    say "li" words

    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
    ir
    -0.09
    do
    -0.08
    orio
    -0.08
     lok
    -0.08
    di
    -0.07
    處
    -0.07
    (k
    -0.07
    ्द
    -0.07
    CEPT
    -0.07
    daa
    -0.07
    POSITIVE LOGITS
     Bung
    0.08
    -af
    0.08
    .assertj
    0.08
    Olá
    0.08
     پ
    0.08
    Af
    0.08
    _putchar
    0.08
    Ай
    0.08
     ناخ
    0.08
     querida
    0.08
    Activations Density 0.000%

    No Known Activations