© 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. 19-RESID-POST-AA
    11. 102809
    Prev
    Next
    INDEX
    Explanations

    right nice

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    useq
    -0.08
     Zustand
    -0.08
    üd
    -0.08
    ուցիչ
    -0.08
    ccan
    -0.08
    ��
    -0.08
    τας
    -0.08
    һы
    -0.08
    ütün
    -0.08
    ृथ
    -0.08
    POSITIVE LOGITS
     сейчас
    0.14
     now
    0.14
     ahora
    0.12
    现在
    0.11
     sekarang
    0.11
     agora
    0.11
    -now
    0.11
     الآن
    0.11
     τώρα
    0.11
     jetzt
    0.11
    Activations Density 0.032%

    No Known Activations