© 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. 102765
    Prev
    Next
    INDEX
    Explanations

    say rinse or set

    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
    nesia
    -0.09
    ��
    -0.09
     الرمل
    -0.08
    nicima
    -0.08
    megiň
    -0.08
     олбор
    -0.08
     الرمال
    -0.08
     nuair
    -0.08
    كومة
    -0.08
    ��
    -0.08
    POSITIVE LOGITS
     "{\"
    0.09
     vuelva
    0.08
     svil
    0.07
     [{"
    0.07
    OK
    0.07
     then
    0.07
    ੌ
    0.07
     volver
    0.07
     vuelve
    0.07
     optionally
    0.07
    Activations Density 0.004%

    No Known Activations