© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    say "ś" word

    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
    rada
    -0.10
    encana
    -0.08
    //'
    -0.08
    cone
    -0.08
    рате
    -0.08
    rated
    -0.07
    rán
    -0.07
    izados
    -0.07
    itatem
    -0.07
    ada
    -0.07
    POSITIVE LOGITS
    ś
    0.10
    ąż
    0.08
    APH
    0.08
     gehe
    0.08
    AG
    0.08
     ag
    0.08
    Ag
    0.08
     gwo
    0.08
     gaan
    0.08
    ाफ
    0.07
    Activations Density 0.000%

    No Known Activations