© 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. 96725
    Prev
    Next
    INDEX
    Explanations

    say "ом"

    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
    iencias
    -0.09
    encias
    -0.09
    iever
    -0.09
    urance
    -0.09
    ্ল
    -0.09
    urrences
    -0.08
    вращ
    -0.08
     lim
    -0.08
    ievements
    -0.08
    itecture
    -0.08
    POSITIVE LOGITS
    ом
    0.12
    మ్
    0.11
    омним
    0.11
    ಮ್
    0.10
    ം
    0.09
    om
    0.09
    ம்
    0.09
    рю
    0.08
    ોમ
    0.08
    ഡി
    0.08
    Activations Density 0.002%

    No Known Activations